启动容器
启动pod容器流程分为三个步骤：
- 启动临时容器
- 启动初始化容器
- 启动业务容器
以上三种类型的启动流程基本一致，均通过调用startContainer函数实现
启动pod容器的源码实现
func (m *kubeGenericRuntimeManager) SyncPod(pod *v1.Pod, podStatus *kubecontainer.PodStatus, pullSecrets []v1.Secret, backOff *flowcontrol.Backoff) (result kubecontainer.PodSyncResult) {
...
// Helper containing boilerplate common to starting all types of containers.
// typeName is a label used to describe this type of container in log messages,
// currently: "container", "init container" or "ephemeral container"
start := func(typeName string, spec *startSpec) error {
startContainerResult := kubecontainer.NewSyncResult(kubecontainer.StartContainer, spec.container.Name)
result.AddSyncResult(startContainerResult)
isInBackOff, msg, err := m.doBackOff(pod, spec.container, podStatus, backOff)
if isInBackOff {
startContainerResult.Fail(err, msg)
klog.V(4).Infof("Backing Off restarting %v %+v in pod %v", typeName, spec.container, format.Pod(pod))
return err
}
klog.V(4).Infof("Creating %v %+v in pod %v", typeName, spec.container, format.Pod(pod))
// NOTE (aramase) podIPs are populated for single stack and dual stack clusters. Send only podIPs.
if msg, err := m.startContainer(podSandboxID, podSandboxConfig, spec, pod, podStatus, pullSecrets, podIP, podIPs); err != nil {
startContainerResult.Fail(err, msg)
// known errors that are logged in other places are logged at higher levels here to avoid
// repetitive log spam
switch {
case err == images.ErrImagePullBackOff:
klog.V(3).Infof("%v start failed: %v: %s", typeName, err, msg)
default:
utilruntime.HandleError(fmt.Errorf("%v start failed: %v: %s", typeName, err, msg))
}
return err
}
return nil
}
// Step 5: start ephemeral containers
// These are started "prior" to init containers to allow running ephemeral containers even when there
// are errors starting an init container. In practice init containers will start first since ephemeral
// containers cannot be specified on pod creation.
if utilfeature.DefaultFeatureGate.Enabled(features.EphemeralContainers) {
for _, idx := range podContainerChanges.EphemeralContainersToStart {
start("ephemeral container", ephemeralContainerStartSpec(&pod.Spec.EphemeralContainers[idx]))
}
}
// Step 6: start the init container.
if container := podContainerChanges.NextInitContainerToStart; container != nil {
// Start the next init container.
if err := start("init container", containerStartSpec(container)); err != nil {
return
}
// Successfully started the container; clear the entry in the failure
klog.V(4).Infof("Completed init container %q for pod %q", container.Name, format.Pod(pod))
}
// Step 7: start containers in podContainerChanges.ContainersToStart.
for _, idx := range podContainerChanges.ContainersToStart {
start("container", containerStartSpec(&pod.Spec.Containers[idx]))
}
return
}
startContainer函数主要逻辑如下：
- 拉取镜像
- 创建容器
- 启动容器
- 执行容器的
postStart钩子(容器启动完毕后要执行的逻辑)
后续我们将对startContainer函数着重讨论
startContainer函数源码实现
kubernetes\pkg\kubelet\kuberuntime\kuberuntime_container.go
func (m *kubeGenericRuntimeManager) startContainer(podSandboxID string, podSandboxConfig *runtimeapi.PodSandboxConfig, spec *startSpec, pod *v1.Pod, podStatus *kubecontainer.PodStatus, pullSecrets []v1.Secret, podIP string, podIPs []string) (string, error) {
container := spec.container
// Step 1: pull the image.
imageRef, msg, err := m.imagePuller.EnsureImageExists(pod, container, pullSecrets, podSandboxConfig)
if err != nil {
s, _ := grpcstatus.FromError(err)
m.recordContainerEvent(pod, container, "", v1.EventTypeWarning, events.FailedToCreateContainer, "Error: %v", s.Message())
return msg, err
}
// Step 2: create the container.
// 生成容器引用，
ref, err := kubecontainer.GenerateContainerRef(pod, container)
if err != nil {
klog.Errorf("Can't make a ref to pod %q, container %v: %v", format.Pod(pod), container.Name, err)
}
klog.V(4).Infof("Generating ref for container %s: %#v", container.Name, ref)
// For a new container, the RestartCount should be 0
// 如果该容器存在，则重启次数加1
restartCount := 0
containerStatus := podStatus.FindContainerStatusByName(container.Name)
if containerStatus != nil {
restartCount = containerStatus.RestartCount + 1
}
// 生成容器配置-获取临时容器ID
target, err := spec.getTargetID(podStatus)
if err != nil {
s, _ := grpcstatus.FromError(err)
m.recordContainerEvent(pod, container, "", v1.EventTypeWarning, events.FailedToCreateContainer, "Error: %v", s.Message())
return s.Message(), ErrCreateContainerConfig
}
// 生成创建容器所需配置：设备列表、volumes列表、环境变量列表、注释列表等
containerConfig, cleanupAction, err := m.generateContainerConfig(container, pod, restartCount, podIP, imageRef, podIPs, target)
if cleanupAction != nil {
defer cleanupAction()
}
if err != nil {
s, _ := grpcstatus.FromError(err)
m.recordContainerEvent(pod, container, "", v1.EventTypeWarning, events.FailedToCreateContainer, "Error: %v", s.Message())
return s.Message(), ErrCreateContainerConfig
}
containerID, err := m.runtimeService.CreateContainer(podSandboxID, containerConfig, podSandboxConfig)
if err != nil {
s, _ := grpcstatus.FromError(err)
m.recordContainerEvent(pod, container, containerID, v1.EventTypeWarning, events.FailedToCreateContainer, "Error: %v", s.Message())
return s.Message(), ErrCreateContainer
}
err = m.internalLifecycle.PreStartContainer(pod, container, containerID)
if err != nil {
s, _ := grpcstatus.FromError(err)
m.recordContainerEvent(pod, container, containerID, v1.EventTypeWarning, events.FailedToStartContainer, "Internal PreStartContainer hook failed: %v", s.Message())
return s.Message(), ErrPreStartHook
}
m.recordContainerEvent(pod, container, containerID, v1.EventTypeNormal, events.CreatedContainer, fmt.Sprintf("Created container %s", container.Name))
if ref != nil {
m.containerRefManager.SetRef(kubecontainer.ContainerID{
Type: m.runtimeName,
ID: containerID,
}, ref)
}
// Step 3: start the container.
err = m.runtimeService.StartContainer(containerID)
if err != nil {
s, _ := grpcstatus.FromError(err)
m.recordContainerEvent(pod, container, containerID, v1.EventTypeWarning, events.FailedToStartContainer, "Error: %v", s.Message())
return s.Message(), kubecontainer.ErrRunContainer
}
m.recordContainerEvent(pod, container, containerID, v1.EventTypeNormal, events.StartedContainer, fmt.Sprintf("Started container %s", container.Name))
// Symlink container logs to the legacy container log location for cluster logging
// support.
// TODO(random-liu): Remove this after cluster logging supports CRI container log path.
// /var/log/containers
containerMeta := containerConfig.GetMetadata()
sandboxMeta := podSandboxConfig.GetMetadata()
legacySymlink := legacyLogSymlink(containerID, containerMeta.Name, sandboxMeta.Name,
sandboxMeta.Namespace)
// podSandboxConfig.LogDirectory="/var/log/pods/default_stakater-reloader-598f958967-ddkl7_2681cb7f-daa4-4620-bb60-1d449709181c"
//
containerLog := filepath.Join(podSandboxConfig.LogDirectory, containerConfig.LogPath)
// only create legacy symlink if containerLog path exists (or the error is not IsNotExist).
// Because if containerLog path does not exist, only dandling legacySymlink is created.
// This dangling legacySymlink is later removed by container gc, so it does not make sense
// to create it in the first place. it happens when journald logging driver is used with docker.
if _, err := m.osInterface.Stat(containerLog); !os.IsNotExist(err) {
if err := m.osInterface.Symlink(containerLog, legacySymlink); err != nil {
klog.Errorf("Failed to create legacy symbolic link %q to container %q log %q: %v",
legacySymlink, containerID, containerLog, err)
}
}
// Step 4: execute the post start hook.
if container.Lifecycle != nil && container.Lifecycle.PostStart != nil {
kubeContainerID := kubecontainer.ContainerID{
Type: m.runtimeName,
ID: containerID,
}
msg, handlerErr := m.runner.Run(kubeContainerID, pod, container, container.Lifecycle.PostStart)
if handlerErr != nil {
m.recordContainerEvent(pod, container, kubeContainerID.ID, v1.EventTypeWarning, events.FailedPostStartHook, msg)
if err := m.killContainer(pod, kubeContainerID, container.Name, "FailedPostStartHook", nil); err != nil {
klog.Errorf("Failed to kill container %q(id=%q) in pod %q: %v, %v",
container.Name, kubeContainerID.String(), format.Pod(pod), ErrPostStartHook, err)
}
return msg, fmt.Errorf("%s: %v", ErrPostStartHook, handlerErr)
}
}
return "", nil
}