有没有办法用 Kubernetes client-go 优雅地结束一个 pod？

Question

主要问题是，是否有办法从client-go sdk完成 pod，我不是要删除 pod，我只想使用 Phase-Status: Completed 完成它。

在代码中，我正在尝试更新 pod 阶段，但它不起作用，它没有返回错误或恐慌，但 pod 没有完成。 我的代码：

func main() {

    // creates the in-cluster config
    config, err := rest.InClusterConfig()
    if err != nil {
        panic(err.Error())
    }
    // creates the clientset
    clientset, err := kubernetes.NewForConfig(config)
    if err != nil {
        panic(err.Error())
    }
    for {

        pods, err := clientset.CoreV1().Pods("ns").List(context.TODO(), metav1.ListOptions{})
        if err != nil {
            panic(err.Error())
        }
        for _, pod := range pods.Items {

            podName:= pod.Name
            if strings.Contains(strings.ToLower(podName), "single-condition") {
            
                fmt.Println("get pods metadatada")
                fmt.Println(pod.Name)
                fmt.Printf("pod.Name %s \n", pod.Name)
                fmt.Printf("Status.Phase %s \n", pod.Status.Phase)
                fmt.Printf("PodIP %s \n", pod.Status.PodIP)

                containers := pod.Status.ContainerStatuses
                if len(containers) > 0 {
                    for _ ,c := range containers {
                        fmt.Printf("c.Name %s \n", c.Name)
                        fmt.Printf("c.State %s \n", c.State)
                        fmt.Printf("c.State.Terminated %s \n", c.State.Terminated)

                        stateTerminated := c.State.Terminated
                        stateRunning := c.State.Running
                        if stateTerminated == nil && stateRunning != nil {
                            fmt.Printf("c.State.Terminated %s \n", c.State.Terminated)
                            fmt.Printf("stateRunning Reason: %s\n", reflect.TypeOf(c.State.Running))

                            getPod, getErr := clientset.CoreV1().Pods("ns").Get(context.TODO(), "single-condition-pipeline-9rqrs-1224102659" , metav1.GetOptions{})
                            if getErr != nil {
                                fmt.Println("error1")
                                panic(fmt.Errorf("Failed to get: %v", getErr))
                            }
                            fmt.Println("update values")
                            fmt.Printf(" getPodName %d \n", getPod.Name)
                            getPod.Status.Phase = "Succeeded"
                            fmt.Println("updated status phase")
                            getContainers := getPod.Status.ContainerStatuses
                            fmt.Printf("len get container %d \n", len(getContainers))
                            _, updateErr := clientset.CoreV1().Pods("argo-workflows").Update(context.TODO(), getPod, metav1.UpdateOptions{})
                            fmt.Println("commit update")
                            if updateErr != nil {
                                fmt.Println("error updated")
                                panic(fmt.Errorf("Failed to update: %v", updateErr))
                            }

                        } else {
                            fmt.Printf("c.State.Terminated %s \n", c.State.Terminated.Reason)
                            //fmt.Println("Not finished ready!!!")
                            //fmt.Printf("c.State.Running %s \n", c.State.Running)
                            //fmt.Printf("c.State.Waiting %s \n", c.State.Waiting)
                        }
                    }
                }
            }
        }
        time.Sleep(10 * time.Second)

    }
}

和一些日志：

single-condition-pipeline-9rqrs-1224102659
pod.Name single-condition-pipeline-9rqrs-1224102659 
Status.Phase Running 
PodIP XXXXXXXXXXXX
c.Name main 
---------------------------------------------------------------------------------------------
c.State {nil &ContainerStateRunning{StartedAt:2021-10-29 04:41:51 +0000 UTC,} nil} 
c.State.Terminated nil 
c.State.Terminated nil 
stateRunning Reason: *v1.ContainerStateRunning
update values
 getPodName %!d(string=single-condition-pipeline-9rqrs-1224102659) 
updated status phase
len get container 2 
commit update
c.Name wait 
c.State {nil &ContainerStateRunning{StartedAt:2021-10-29 04:41:51 +0000 UTC,} nil} 
c.State.Terminated nil 
c.State.Terminated nil 
stateRunning Reason: *v1.ContainerStateRunning
update values
 getPodName %!d(string=single-condition-pipeline-9rqrs-1224102659) 
updated status phase
len get container 2 
---------------------------------------------------------------------------------------------
commit update
---------------------------------------------------------------------------------------------
get pods metadatada
single-condition-pipeline-9rqrs-1224102659
pod.Name single-condition-pipeline-9rqrs-1224102659 
Status.Phase Running 
PodIP XXXXXXXXXX 
c.Name main 
c.State {nil &ContainerStateRunning{StartedAt:2021-10-29 04:41:51 +0000 UTC,} nil} 
c.State.Terminated nil 
c.State.Terminated nil 
stateRunning Reason: *v1.ContainerStateRunning
update values
 getPodName %!d(string=single-condition-pipeline-9rqrs-1224102659) 
updated status phase
len get container 2 
commit update
c.Name wait 
c.State {nil &ContainerStateRunning{StartedAt:2021-10-29 04:41:51 +0000 UTC,} nil} 
c.State.Terminated nil 
c.State.Terminated nil 
stateRunning Reason: *v1.ContainerStateRunning
update values
 getPodName %!d(string=single-condition-pipeline-9rqrs-1224102659) 
updated status phase
len get container 2 
commit update

所以在这里： https : //kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#pod-readiness-status ，它提到了一个补丁，但我不知道如何使用它，所以如果有人可以提供帮助我或者如果有另一种方法来完成它。

Answer 1

您不能在 Pod status字段中设置phase或其他任何内容，它是只读的。 按照波德生命周期文档您的吊舱将有一个阶段Succeeded后，“在群所有容器中的成功已经终止，并不会重新启动。” 因此，只有当您可以导致所有 pod 的容器以状态代码0退出并且 pod restartPolicy设置为onFailure或Never ，如果设置为Always （默认值），那么容器最终将重新启动并且您的pod 最终会返回到Running阶段。

总之，您无法直接通过 Kube API 执行您尝试执行的操作。 你必须：

1. 确保您的 pod 具有可以支持Succeeded阶段的restartPolicy 。
2. 导致您的应用程序终止，可能是通过向它发送SIGINT或SIGTERM ，或者可能是通过它自己的 API 命令它。