github/kubernetes
1
0
Fork 0
mirror of https://github.com/k3s-io/kubernetes.git synced 2025-09-21 01:50:55 +00:00
Code Issues Projects Releases Wiki Activity

kubelet: Delay writing a terminal phase until the pod is terminated

Browse Source 
Other components must know when the Kubelet has released critical
resources for terminal pods. Do not set the phase in the apiserver
to terminal until all containers are stopped and cannot restart.

As a consequence of this change, the Kubelet must explicitly transition
a terminal pod to the terminating state in the pod worker which is
handled by returning a new isTerminal boolean from syncPod.

Finally, if a pod with init containers hasn't been initialized yet,
don't default container statuses or not yet attempted init containers
to the unknown failure state.
This commit is contained in:
Clayton Coleman
2022-02-26 14:36:51 -05:00
parent 9cb9a29f34
commit 69a3820214
10 changed files with 734 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
pkg/kubelet/kubelet.go
View File

@@ -1452,24 +1452,36 @@ func (kl *Kubelet) Run(updates <-chan kubetypes.PodUpdate) {
}
// syncPod is the transaction script for the sync of a single pod (setting up)
// a pod. The reverse (teardown) is handled in syncTerminatingPod and
// syncTerminatedPod. If syncPod exits without error, then the pod runtime
// state is in sync with the desired configuration state (pod is running).
// If syncPod exits with a transient error, the next invocation of syncPod
// is expected to make progress towards reaching the runtime state.
// a pod. This method is reentrant and expected to converge a pod towards the
// desired state of the spec. The reverse (teardown) is handled in
// syncTerminatingPod and syncTerminatedPod. If syncPod exits without error,
// then the pod runtime state is in sync with the desired configuration state
// (pod is running). If syncPod exits with a transient error, the next
// invocation of syncPod is expected to make progress towards reaching the
// runtime state. syncPod exits with isTerminal when the pod was detected to
// have reached a terminal lifecycle phase due to container exits (for
// RestartNever or RestartOnFailure) and the next method invoked will by
// syncTerminatingPod.
//
// Arguments:
//
// o - the SyncPodOptions for this invocation
// updateType - whether this is a create (first time) or an update, should
// only be used for metrics since this method must be reentrant
// pod - the pod that is being set up
// mirrorPod - the mirror pod known to the kubelet for this pod, if any
// podStatus - the most recent pod status observed for this pod which can
// be used to determine the set of actions that should be taken during
// this loop of syncPod
//
// The workflow is:
// * Kill the pod immediately if update type is SyncPodKill
// * If the pod is being created, record pod worker start latency
// * Call generateAPIPodStatus to prepare an v1.PodStatus for the pod
// * If the pod is being seen as running for the first time, record pod
// start latency
// * Update the status of the pod in the status manager
// * Kill the pod if it should not be running due to soft admission
// * Stop the pod's containers if it should not be running due to soft
// admission
// * Ensure any background tracking for a runnable pod is started
// * Create a mirror pod if the pod is a static pod, and does not
// already have a mirror pod
// * Create the data directories for the pod if they do not exist
@@ -1483,10 +1495,12 @@ func (kl *Kubelet) Run(updates <-chan kubetypes.PodUpdate) {
//
// This operation writes all events that are dispatched in order to provide
// the most accurate information possible about an error situation to aid debugging.
// Callers should not throw an event if this operation returns an error.
func (kl *Kubelet) syncPod(ctx context.Context, updateType kubetypes.SyncPodType, pod, mirrorPod *v1.Pod, podStatus *kubecontainer.PodStatus) error {
// Callers should not write an event if this operation returns an error.
func (kl *Kubelet) syncPod(ctx context.Context, updateType kubetypes.SyncPodType, pod, mirrorPod *v1.Pod, podStatus *kubecontainer.PodStatus) (isTerminal bool, err error) {
klog.V(4).InfoS("syncPod enter", "pod", klog.KObj(pod), "podUID", pod.UID)
defer klog.V(4).InfoS("syncPod exit", "pod", klog.KObj(pod), "podUID", pod.UID)
defer func() {
klog.V(4).InfoS("syncPod exit", "pod", klog.KObj(pod), "podUID", pod.UID, "isTerminal", isTerminal)
}()
// Latency measurements for the main workflow are relative to the
// first time the pod was seen by kubelet.
@@ -1518,11 +1532,17 @@ func (kl *Kubelet) syncPod(ctx context.Context, updateType kubetypes.SyncPodType
for _, ipInfo := range apiPodStatus.PodIPs {
podStatus.IPs = append(podStatus.IPs, ipInfo.IP)
}
if len(podStatus.IPs) == 0 && len(apiPodStatus.PodIP) > 0 {
podStatus.IPs = []string{apiPodStatus.PodIP}
}
// If the pod is terminal, we don't need to continue to setup the pod
if apiPodStatus.Phase == v1.PodSucceeded || apiPodStatus.Phase == v1.PodFailed {
kl.statusManager.SetPodStatus(pod, apiPodStatus)
isTerminal = true
return isTerminal, nil
}
// If the pod should not be running, we request the pod's containers be stopped. This is not the same
// as termination (we want to stop the pod, but potentially restart it later if soft admission allows
// it later). Set the status and phase appropriately
@@ -1572,13 +1592,13 @@ func (kl *Kubelet) syncPod(ctx context.Context, updateType kubetypes.SyncPodType
// Return an error to signal that the sync loop should back off.
syncErr = fmt.Errorf("pod cannot be run: %s", runnable.Message)
}
return syncErr
return false, syncErr
}
// If the network plugin is not ready, only start the pod if it uses the host network
if err := kl.runtimeState.networkErrors(); err != nil && !kubecontainer.IsHostNetworkPod(pod) {
kl.recorder.Eventf(pod, v1.EventTypeWarning, events.NetworkNotReady, "%s: %v", NetworkNotReadyErrorMsg, err)
return fmt.Errorf("%s: %v", NetworkNotReadyErrorMsg, err)
return false, fmt.Errorf("%s: %v", NetworkNotReadyErrorMsg, err)
}
// ensure the kubelet knows about referenced secrets or configmaps used by the pod
@@ -1635,7 +1655,7 @@ func (kl *Kubelet) syncPod(ctx context.Context, updateType kubetypes.SyncPodType
}
if err := pcm.EnsureExists(pod); err != nil {
kl.recorder.Eventf(pod, v1.EventTypeWarning, events.FailedToCreatePodContainer, "unable to ensure pod container exists: %v", err)
return fmt.Errorf("failed to ensure that the pod: %v cgroups exist and are correctly applied: %v", pod.UID, err)
return false, fmt.Errorf("failed to ensure that the pod: %v cgroups exist and are correctly applied: %v", pod.UID, err)
}
}
}
@@ -1676,7 +1696,7 @@ func (kl *Kubelet) syncPod(ctx context.Context, updateType kubetypes.SyncPodType
if err := kl.makePodDataDirs(pod); err != nil {
kl.recorder.Eventf(pod, v1.EventTypeWarning, events.FailedToMakePodDataDirectories, "error making pod data directories: %v", err)
klog.ErrorS(err, "Unable to make pod data directories for pod", "pod", klog.KObj(pod))
return err
return false, err
}
// Volume manager will not mount volumes for terminating pods
@@ -1686,7 +1706,7 @@ func (kl *Kubelet) syncPod(ctx context.Context, updateType kubetypes.SyncPodType
if err := kl.volumeManager.WaitForAttachAndMount(pod); err != nil {
kl.recorder.Eventf(pod, v1.EventTypeWarning, events.FailedMountVolume, "Unable to attach or mount volumes: %v", err)
klog.ErrorS(err, "Unable to attach or mount volumes for pod; skipping pod", "pod", klog.KObj(pod))
return err
return false, err
}
}
@@ -1702,14 +1722,14 @@ func (kl *Kubelet) syncPod(ctx context.Context, updateType kubetypes.SyncPodType
if r.Error != kubecontainer.ErrCrashLoopBackOff && r.Error != images.ErrImagePullBackOff {
// Do not record an event here, as we keep all event logging for sync pod failures
// local to container runtime, so we get better errors.
return err
return false, err
}
}
return nil
return false, nil
}
return nil
return false, nil
}
// syncTerminatingPod is expected to terminate all running containers in a pod. Once this method