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，我只想用 Phase-状态：已完成。

在代码中，我正在尝试更新 pod 阶段，但它不起作用，它不会返回错误或恐慌，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)

    }
}

还有一些日志：

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，所以如果有人可以帮助我或者是否有其他方法可以完成它。

Answer 1

您不能在 Pod status 字段中设置 phase 或其他任何内容，它是 read only。根据Pod Lifecycle 文档，在“Pod 中的所有容器都已成功终止，并且不会重新启动”之后，您的 pod 将具有Succeeded 的阶段。可能会导致您的所有 pod 的容器以状态码 0 退出，如果 pod restartPolicy 设置为 onFailure 或 Never，如果它设置为 Always（默认值），那么容器最终将重新启动，您的 pod 最终将返回到 Running 阶段。

总而言之，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. 可能通过发送SIGINT 或SIGTERM 或通过其自己的API 命令来终止您的应用程序。