[原始碼分析] kubelet原始碼分析（三）之 Pod的建立

func (kl *Kubelet) syncLoopIteration(configCh <-chan kubetypes.PodUpdate, handler SyncHandler,
syncCh <-chan time.Time, housekeepingCh <-chan time.Time, plegCh <-chan *pleg.PodLifecycleEvent) bool {
select {
case u, open := <-configCh:
// Update from a config source; dispatch it to the right handler
// callback.
if !open {
glog.Errorf("Update channel is closed. Exiting the sync loop.")
return false
}

switch u.Op {
case kubetypes.ADD:
glog.V(2).Infof("SyncLoop (ADD, %q): %q", u.Source, format.Pods(u.Pods))
// After restarting, kubelet will get all existing pods through
// ADD as if they are new pods. These pods will then go through the
// admission process and *may* be rejected. This can be resolved
// once we have checkpointing.
handler.HandlePodAdditions(u.Pods)
case kubetypes.UPDATE:
glog.V(2).Infof("SyncLoop (UPDATE, %q): %q", u.Source, format.PodsWithDeletionTimestamps(u.Pods))
handler.HandlePodUpdates(u.Pods)
case kubetypes.REMOVE:
glog.V(2).Infof("SyncLoop (REMOVE, %q): %q", u.Source, format.Pods(u.Pods))
handler.HandlePodRemoves(u.Pods)
case kubetypes.RECONCILE:
glog.V(4).Infof("SyncLoop (RECONCILE, %q): %q", u.Source, format.Pods(u.Pods))
handler.HandlePodReconcile(u.Pods)
case kubetypes.DELETE:
glog.V(2).Infof("SyncLoop (DELETE, %q): %q", u.Source, format.Pods(u.Pods))
// DELETE is treated as a UPDATE because of graceful deletion.
handler.HandlePodUpdates(u.Pods)
case kubetypes.RESTORE:
glog.V(2).Infof("SyncLoop (RESTORE, %q): %q", u.Source, format.Pods(u.Pods))
// These are pods restored from the checkpoint. Treat them as new
// pods.
handler.HandlePodAdditions(u.Pods)
case kubetypes.SET:
// TODO: Do we want to support this?
glog.Errorf("Kubelet does not support snapshot update")
}

if u.Op != kubetypes.RESTORE {
// If the update type is RESTORE, it means that the update is from
// the pod checkpoints and may be incomplete. Do not mark the
// source as ready.

// Mark the source ready after receiving at least one update from the
// source. Once all the sources are marked ready, various cleanup
// routines will start reclaiming resources. It is important that this
// takes place only after kubelet calls the update handler to process
// the update to ensure the internal pod cache is up-to-date.
kl.sourcesReady.AddSource(u.Source)
}
case e := <-plegCh:
if isSyncPodWorthy(e) {
// PLEG event for a pod; sync it.
if pod, ok := kl.podManager.GetPodByUID(e.ID); ok {
glog.V(2).Infof("SyncLoop (PLEG): %q, event: %#v", format.Pod(pod), e)
handler.HandlePodSyncs([]*v1.Pod{pod})
} else {
// If the pod no longer exists, ignore the event.
glog.V(4).Infof("SyncLoop (PLEG): ignore irrelevant event: %#v", e)
}
}

if e.Type == pleg.ContainerDied {
if containerID, ok := e.Data.(string); ok {
kl.cleanUpContainersInPod(e.ID, containerID)
}
}
case <-syncCh:
// Sync pods waiting for sync
podsToSync := kl.getPodsToSync()
if len(podsToSync) == 0 {
break
}
glog.V(4).Infof("SyncLoop (SYNC): %d pods; %s", len(podsToSync), format.Pods(podsToSync))
handler.HandlePodSyncs(podsToSync)
case update := <-kl.livenessManager.Updates():
if update.Result == proberesults.Failure {
// The liveness manager detected a failure; sync the pod.

// We should not use the pod from livenessManager, because it is never updated after
// initialization.
pod, ok := kl.podManager.GetPodByUID(update.PodUID)
if !ok {
// If the pod no longer exists, ignore the update.
glog.V(4).Infof("SyncLoop (container unhealthy): ignore irrelevant update: %#v", update)
break
}
glog.V(1).Infof("SyncLoop (container unhealthy): %q", format.Pod(pod))
handler.HandlePodSyncs([]*v1.Pod{pod})
}
case <-housekeepingCh:
if !kl.sourcesReady.AllReady() {
// If the sources aren't ready or volume manager has not yet synced the states,
// skip housekeeping, as we may accidentally delete pods from unready sources.
glog.V(4).Infof("SyncLoop (housekeeping, skipped): sources aren't ready yet.")
} else {
glog.V(4).Infof("SyncLoop (housekeeping)")
if err := handler.HandlePodCleanups(); err != nil {
glog.Errorf("Failed cleaning pods: %v", err)
}
}
}
return true
}

// SyncHandler is an interface implemented by Kubelet, for testability
type SyncHandler interface {
HandlePodAdditions(pods []*v1.Pod)
HandlePodUpdates(pods []*v1.Pod)
HandlePodRemoves(pods []*v1.Pod)
HandlePodReconcile(pods []*v1.Pod)
HandlePodSyncs(pods []*v1.Pod)
HandlePodCleanups() error
}

// HandlePodAdditions is the callback in SyncHandler for pods being added from
// a config source.
func (kl *Kubelet) HandlePodAdditions(pods []*v1.Pod) {
start := kl.clock.Now()
sort.Sort(sliceutils.PodsByCreationTime(pods))
for _, pod := range pods {
...
}
}

for _, pod := range pods {
// Responsible for checking limits in resolv.conf
if kl.dnsConfigurer != nil && kl.dnsConfigurer.ResolverConfig != "" {
kl.dnsConfigurer.CheckLimitsForResolvConf()
}
existingPods := kl.podManager.GetPods()
// Always add the pod to the pod manager. Kubelet relies on the pod
// manager as the source of truth for the desired state. If a pod does
// not exist in the pod manager, it means that it has been deleted in
// the apiserver and no action (other than cleanup) is required.
kl.podManager.AddPod(pod)
...
}

if kubepod.IsMirrorPod(pod) {
kl.handleMirrorPod(pod, start)
continue
}

if !kl.podIsTerminated(pod) {
// Only go through the admission process if the pod is not
// terminated.

// We failed pods that we rejected, so activePods include all admitted
// pods that are alive.
activePods := kl.filterOutTerminatedPods(existingPods)

// Check if we can admit the pod; if not, reject it.
if ok, reason, message := kl.canAdmitPod(activePods, pod); !ok {
kl.rejectPod(pod, reason, message)
continue
}
}

mirrorPod, _ := kl.podManager.GetMirrorPodByPod(pod)
kl.dispatchWork(pod, kubetypes.SyncPodCreate, mirrorPod, start)

kl.probeManager.AddPod(pod)

// HandlePodUpdates is the callback in the SyncHandler interface for pods
// being updated from a config source.
func (kl *Kubelet) HandlePodUpdates(pods []*v1.Pod) {
start := kl.clock.Now()
for _, pod := range pods {
...
}
}

for _, pod := range pods {
// Responsible for checking limits in resolv.conf
if kl.dnsConfigurer != nil && kl.dnsConfigurer.ResolverConfig != "" {
kl.dnsConfigurer.CheckLimitsForResolvConf()
}
kl.podManager.UpdatePod(pod)
...
}

if kubepod.IsMirrorPod(pod) {
kl.handleMirrorPod(pod, start)
continue
}

// TODO: Evaluate if we need to validate and reject updates.

mirrorPod, _ := kl.podManager.GetMirrorPodByPod(pod)
kl.dispatchWork(pod, kubetypes.SyncPodUpdate, mirrorPod, start)

// HandlePodRemoves is the callback in the SyncHandler interface for pods
// being removed from a config source.
func (kl *Kubelet) HandlePodRemoves(pods []*v1.Pod) {
start := kl.clock.Now()
for _, pod := range pods {
...
}
}

for _, pod := range pods {
kl.podManager.DeletePod(pod)
...
}

if kubepod.IsMirrorPod(pod) {
kl.handleMirrorPod(pod, start)
continue
}

// Deletion is allowed to fail because the periodic cleanup routine
// will trigger deletion again.
if err := kl.deletePod(pod); err != nil {
glog.V(2).Infof("Failed to delete pod %q, err: %v", format.Pod(pod), err)
}

// deletePod deletes the pod from the internal state of the kubelet by:
// 1.stopping the associated pod worker asynchronously
// 2.signaling to kill the pod by sending on the podKillingCh channel
//
// deletePod returns an error if not all sources are ready or the pod is not
// found in the runtime cache.
func (kl *Kubelet) deletePod(pod *v1.Pod) error {
if pod == nil {
return fmt.Errorf("deletePod does not allow nil pod")
}
if !kl.sourcesReady.AllReady() {
// If the sources aren't ready, skip deletion, as we may accidentally delete pods
// for sources that haven't reported yet.
return fmt.Errorf("skipping delete because sources aren't ready yet")
}
kl.podWorkers.ForgetWorker(pod.UID)

// Runtime cache may not have been updated to with the pod, but it's okay
// because the periodic cleanup routine will attempt to delete again later.
runningPods, err := kl.runtimeCache.GetPods()
if err != nil {
return fmt.Errorf("error listing containers: %v", err)
}
runningPod := kubecontainer.Pods(runningPods).FindPod("", pod.UID)
if runningPod.IsEmpty() {
return fmt.Errorf("pod not found")
}
podPair := kubecontainer.PodPair{APIPod: pod, RunningPod: &runningPod}

kl.podKillingCh <- &podPair
// TODO: delete the mirror pod here?

// We leave the volume/directory cleanup to the periodic cleanup routine.
return nil
}

kl.probeManager.RemovePod(pod)

// HandlePodReconcile is the callback in the SyncHandler interface for pods
// that should be reconciled.
func (kl *Kubelet) HandlePodReconcile(pods []*v1.Pod) {
start := kl.clock.Now()
for _, pod := range pods {
...
}
}

for _, pod := range pods {
// Update the pod in pod manager, status manager will do periodically reconcile according
// to the pod manager.
kl.podManager.UpdatePod(pod)
...
}

// Reconcile Pod "Ready" condition if necessary. Trigger sync pod for reconciliation.
if status.NeedToReconcilePodReadiness(pod) {
mirrorPod, _ := kl.podManager.GetMirrorPodByPod(pod)
kl.dispatchWork(pod, kubetypes.SyncPodSync, mirrorPod, start)
}

// After an evicted pod is synced, all dead containers in the pod can be removed.
if eviction.PodIsEvicted(pod.Status) {
if podStatus, err := kl.podCache.Get(pod.UID); err == nil {
kl.containerDeletor.deleteContainersInPod("", podStatus, true)
}
}

// HandlePodSyncs is the callback in the syncHandler interface for pods
// that should be dispatched to pod workers for sync.
func (kl *Kubelet) HandlePodSyncs(pods []*v1.Pod) {
start := kl.clock.Now()
for _, pod := range pods {
mirrorPod, _ := kl.podManager.GetMirrorPodByPod(pod)
kl.dispatchWork(pod, kubetypes.SyncPodSync, mirrorPod, start)
}
}

// HandlePodCleanups performs a series of cleanup work, including terminating
// pod workers, killing unwanted pods, and removing orphaned volumes/pod
// directories.
// NOTE: This function is executed by the main sync loop, so it
// should not contain any blocking calls.
func (kl *Kubelet) HandlePodCleanups() error {
// The kubelet lacks checkpointing, so we need to introspect the set of pods
// in the cgroup tree prior to inspecting the set of pods in our pod manager.
// this ensures our view of the cgroup tree does not mistakenly observe pods
// that are added after the fact...
var (
cgroupPods map[types.UID]cm.CgroupName
errerror
)
if kl.cgroupsPerQOS {
pcm := kl.containerManager.NewPodContainerManager()
cgroupPods, err = pcm.GetAllPodsFromCgroups()
if err != nil {
return fmt.Errorf("failed to get list of pods that still exist on cgroup mounts: %v", err)
}
}
...
}

allPods, mirrorPods := kl.podManager.GetPodsAndMirrorPods()
// Pod phase progresses monotonically. Once a pod has reached a final state,
// it should never leave regardless of the restart policy. The statuses
// of such pods should not be changed, and there is no need to sync them.
// TODO: the logic here does not handle two cases:
//1. If the containers were removed immediately after they died, kubelet
//may fail to generate correct statuses, let alone filtering correctly.
//2. If kubelet restarted before writing the terminated status for a pod
//to the apiserver, it could still restart the terminated pod (even
//though the pod was not considered terminated by the apiserver).
// These two conditions could be alleviated by checkpointing kubelet.
activePods := kl.filterOutTerminatedPods(allPods)

desiredPods := make(map[types.UID]empty)
for _, pod := range activePods {
desiredPods[pod.UID] = empty{}
}

// Stop the workers for no-longer existing pods.
// TODO: is here the best place to forget pod workers?
kl.podWorkers.ForgetNonExistingPodWorkers(desiredPods)
kl.probeManager.CleanupPods(activePods)

runningPods, err := kl.runtimeCache.GetPods()
if err != nil {
glog.Errorf("Error listing containers: %#v", err)
return err
}
for _, pod := range runningPods {
if _, found := desiredPods[pod.ID]; !found {
kl.podKillingCh <- &kubecontainer.PodPair{APIPod: nil, RunningPod: pod}
}
}

kl.removeOrphanedPodStatuses(allPods, mirrorPods)

// Remove any orphaned volumes.
// Note that we pass all pods (including terminated pods) to the function,
// so that we don't remove volumes associated with terminated but not yet
// deleted pods.
err = kl.cleanupOrphanedPodDirs(allPods, runningPods)
if err != nil {
// We want all cleanup tasks to be run even if one of them failed. So
// we just log an error here and continue other cleanup tasks.
// This also applies to the other clean up tasks.
glog.Errorf("Failed cleaning up orphaned pod directories: %v", err)
}

// Remove any orphaned mirror pods.
kl.podManager.DeleteOrphanedMirrorPods()

// Remove any cgroups in the hierarchy for pods that are no longer running.
if kl.cgroupsPerQOS {
kl.cleanupOrphanedPodCgroups(cgroupPods, activePods)
}

kl.backOff.GC()

// dispatchWork starts the asynchronous sync of the pod in a pod worker.
// If the pod is terminated, dispatchWork
func (kl *Kubelet) dispatchWork(pod *v1.Pod, syncType kubetypes.SyncPodType, mirrorPod *v1.Pod, start time.Time) {
if kl.podIsTerminated(pod) {
if pod.DeletionTimestamp != nil {
// If the pod is in a terminated state, there is no pod worker to
// handle the work item. Check if the DeletionTimestamp has been
// set, and force a status update to trigger a pod deletion request
// to the apiserver.
kl.statusManager.TerminatePod(pod)
}
return
}
...
}

// Run the sync in an async worker.
kl.podWorkers.UpdatePod(&UpdatePodOptions{
Pod:pod,
MirrorPod:mirrorPod,
UpdateType: syncType,
OnCompleteFunc: func(err error) {
if err != nil {
metrics.PodWorkerLatency.WithLabelValues(syncType.String()).Observe(metrics.SinceInMicroseconds(start))
}
},
})

// Note the number of containers for new pods.
if syncType == kubetypes.SyncPodCreate {
metrics.ContainersPerPodCount.Observe(float64(len(pod.Spec.Containers)))
}

// PodWorkers is an abstract interface for testability.
type PodWorkers interface {
UpdatePod(options *UpdatePodOptions)
ForgetNonExistingPodWorkers(desiredPods map[types.UID]empty)
ForgetWorker(uid types.UID)
}

// Apply the new setting to the specified pod.
// If the options provide an OnCompleteFunc, the function is invoked if the update is accepted.
// Update requests are ignored if a kill pod request is pending.
func (p *podWorkers) UpdatePod(options *UpdatePodOptions) {
pod := options.Pod
uid := pod.UID
var podUpdates chan UpdatePodOptions
var exists bool

p.podLock.Lock()
defer p.podLock.Unlock()
if podUpdates, exists = p.podUpdates[uid]; !exists {
// We need to have a buffer here, because checkForUpdates() method that
// puts an update into channel is called from the same goroutine where
// the channel is consumed. However, it is guaranteed that in such case
// the channel is empty, so buffer of size 1 is enough.
podUpdates = make(chan UpdatePodOptions, 1)
p.podUpdates[uid] = podUpdates

// Creating a new pod worker either means this is a new pod, or that the
// kubelet just restarted. In either case the kubelet is willing to believe
// the status of the pod for the first pod worker sync. See corresponding
// comment in syncPod.
go func() {
defer runtime.HandleCrash()
p.managePodLoop(podUpdates)
}()
}
if !p.isWorking[pod.UID] {
p.isWorking[pod.UID] = true
podUpdates <- *options
} else {
// if a request to kill a pod is pending, we do not let anything overwrite that request.
update, found := p.lastUndeliveredWorkUpdate[pod.UID]
if !found || update.UpdateType != kubetypes.SyncPodKill {
p.lastUndeliveredWorkUpdate[pod.UID] = *options
}
}
}

klet.podWorkers = newPodWorkers(klet.syncPod, kubeDeps.Recorder, klet.workQueue, klet.resyncInterval, backOffPeriod, klet.podCache)

func newPodWorkers(syncPodFn syncPodFnType, recorder record.EventRecorder, workQueue queue.WorkQueue,
resyncInterval, backOffPeriod time.Duration, podCache kubecontainer.Cache) *podWorkers {
return &podWorkers{
podUpdates:map[types.UID]chan UpdatePodOptions{},
isWorking:map[types.UID]bool{},
lastUndeliveredWorkUpdate: map[types.UID]UpdatePodOptions{},
syncPodFn:syncPodFn,
recorder:recorder,
workQueue:workQueue,
resyncInterval:resyncInterval,
backOffPeriod:backOffPeriod,
podCache:podCache,
}
}

func (p *podWorkers) managePodLoop(podUpdates <-chan UpdatePodOptions) {
var lastSyncTime time.Time
for update := range podUpdates {
err := func() error {
podUID := update.Pod.UID
// This is a blocking call that would return only if the cache
// has an entry for the pod that is newer than minRuntimeCache
// Time. This ensures the worker doesn't start syncing until
// after the cache is at least newer than the finished time of
// the previous sync.
status, err := p.podCache.GetNewerThan(podUID, lastSyncTime)
if err != nil {
// This is the legacy event thrown by manage pod loop
// all other events are now dispatched from syncPodFn
p.recorder.Eventf(update.Pod, v1.EventTypeWarning, events.FailedSync, "error determining status: %v", err)
return err
}
err = p.syncPodFn(syncPodOptions{
mirrorPod:update.MirrorPod,
pod:update.Pod,
podStatus:status,
killPodOptions: update.KillPodOptions,
updateType:update.UpdateType,
})
lastSyncTime = time.Now()
return err
}()
// notify the call-back function if the operation succeeded or not
if update.OnCompleteFunc != nil {
update.OnCompleteFunc(err)
}
if err != nil {
// IMPORTANT: we do not log errors here, the syncPodFn is responsible for logging errors
glog.Errorf("Error syncing pod %s (%q), skipping: %v", update.Pod.UID, format.Pod(update.Pod), err)
}
p.wrapUp(update.Pod.UID, err)
}
}

// syncPodOptions provides the arguments to a SyncPod operation.
type syncPodOptions struct {
// the mirror pod for the pod to sync, if it is a static pod
mirrorPod *v1.Pod
// pod to sync
pod *v1.Pod
// the type of update (create, update, sync)
updateType kubetypes.SyncPodType
// the current status
podStatus *kubecontainer.PodStatus
// if update type is kill, use the specified options to kill the pod.
killPodOptions *KillPodOptions
}

func (kl *Kubelet) syncPod(o syncPodOptions) error {
// pull out the required options
pod := o.pod
mirrorPod := o.mirrorPod
podStatus := o.podStatus
updateType := o.updateType
...
}

// if we want to kill a pod, do it now!
if updateType == kubetypes.SyncPodKill {
killPodOptions := o.killPodOptions
if killPodOptions == nil || killPodOptions.PodStatusFunc == nil {
return fmt.Errorf("kill pod options are required if update type is kill")
}
apiPodStatus := killPodOptions.PodStatusFunc(pod, podStatus)
kl.statusManager.SetPodStatus(pod, apiPodStatus)
// we kill the pod with the specified grace period since this is a termination
if err := kl.killPod(pod, nil, podStatus, killPodOptions.PodTerminationGracePeriodSecondsOverride); err != nil {
kl.recorder.Eventf(pod, v1.EventTypeWarning, events.FailedToKillPod, "error killing pod: %v", err)
// there was an error killing the pod, so we return that error directly
utilruntime.HandleError(err)
return err
}
return nil
}

// Latency measurements for the main workflow are relative to the
// first time the pod was seen by the API server.
var firstSeenTime time.Time
if firstSeenTimeStr, ok := pod.Annotations[kubetypes.ConfigFirstSeenAnnotationKey]; ok {
firstSeenTime = kubetypes.ConvertToTimestamp(firstSeenTimeStr).Get()
}

// Record pod worker start latency if being created
// TODO: make pod workers record their own latencies
if updateType == kubetypes.SyncPodCreate {
if !firstSeenTime.IsZero() {
// This is the first time we are syncing the pod. Record the latency
// since kubelet first saw the pod if firstSeenTime is set.
metrics.PodWorkerStartLatency.Observe(metrics.SinceInMicroseconds(firstSeenTime))
} else {
glog.V(3).Infof("First seen time not recorded for pod %q", pod.UID)
}
}

// Generate final API pod status with pod and status manager status
apiPodStatus := kl.generateAPIPodStatus(pod, podStatus)
// The pod IP may be changed in generateAPIPodStatus if the pod is using host network. (See #24576)
// TODO(random-liu): After writing pod spec into container labels, check whether pod is using host network, and
// set pod IP to hostIP directly in runtime.GetPodStatus
podStatus.IP = apiPodStatus.PodIP

// Record the time it takes for the pod to become running.
existingStatus, ok := kl.statusManager.GetPodStatus(pod.UID)
if !ok || existingStatus.Phase == v1.PodPending && apiPodStatus.Phase == v1.PodRunning &&
!firstSeenTime.IsZero() {
metrics.PodStartLatency.Observe(metrics.SinceInMicroseconds(firstSeenTime))
}

runnable := kl.canRunPod(pod)
if !runnable.Admit {
// Pod is not runnable; update the Pod and Container statuses to why.
apiPodStatus.Reason = runnable.Reason
apiPodStatus.Message = runnable.Message
// Waiting containers are not creating.
const waitingReason = "Blocked"
for _, cs := range apiPodStatus.InitContainerStatuses {
if cs.State.Waiting != nil {
cs.State.Waiting.Reason = waitingReason
}
}
for _, cs := range apiPodStatus.ContainerStatuses {
if cs.State.Waiting != nil {
cs.State.Waiting.Reason = waitingReason
}
}
}

// Update status in the status manager
kl.statusManager.SetPodStatus(pod, apiPodStatus)

// Kill pod if it should not be running
if !runnable.Admit || pod.DeletionTimestamp != nil || apiPodStatus.Phase == v1.PodFailed {
var syncErr error
if err := kl.killPod(pod, nil, podStatus, nil); err != nil {
kl.recorder.Eventf(pod, v1.EventTypeWarning, events.FailedToKillPod, "error killing pod: %v", err)
syncErr = fmt.Errorf("error killing pod: %v", err)
utilruntime.HandleError(syncErr)
} else {
if !runnable.Admit {
// There was no error killing the pod, but the pod cannot be run.
// Return an error to signal that the sync loop should back off.
syncErr = fmt.Errorf("pod cannot be run: %s", runnable.Message)
}
}
return syncErr
}

// If the network plugin is not ready, only start the pod if it uses the host network
if rs := kl.runtimeState.networkErrors(); len(rs) != 0 && !kubecontainer.IsHostNetworkPod(pod) {
kl.recorder.Eventf(pod, v1.EventTypeWarning, events.NetworkNotReady, "%s: %v", NetworkNotReadyErrorMsg, rs)
return fmt.Errorf("%s: %v", NetworkNotReadyErrorMsg, rs)
}

// Create Cgroups for the pod and apply resource parameters
// to them if cgroups-per-qos flag is enabled.
pcm := kl.containerManager.NewPodContainerManager()
// If pod has already been terminated then we need not create
// or update the pod's cgroup
if !kl.podIsTerminated(pod) {
// When the kubelet is restarted with the cgroups-per-qos
// flag enabled, all the pod's running containers
// should be killed intermittently and brought back up
// under the qos cgroup hierarchy.
// Check if this is the pod's first sync
firstSync := true
for _, containerStatus := range apiPodStatus.ContainerStatuses {
if containerStatus.State.Running != nil {
firstSync = false
break
}
}
// Don't kill containers in pod if pod's cgroups already
// exists or the pod is running for the first time
podKilled := false
if !pcm.Exists(pod) && !firstSync {
if err := kl.killPod(pod, nil, podStatus, nil); err == nil {
podKilled = true
}
}
...

// Create and Update pod's Cgroups
// Don't create cgroups for run once pod if it was killed above
// The current policy is not to restart the run once pods when
// the kubelet is restarted with the new flag as run once pods are
// expected to run only once and if the kubelet is restarted then
// they are not expected to run again.
// We don't create and apply updates to cgroup if its a run once pod and was killed above
if !(podKilled && pod.Spec.RestartPolicy == v1.RestartPolicyNever) {
if !pcm.Exists(pod) {
if err := kl.containerManager.UpdateQOSCgroups(); err != nil {
glog.V(2).Infof("Failed to update QoS cgroups while syncing pod: %v", err)
}
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)
}
}
}

if err := kl.containerManager.UpdateQOSCgroups(); err != nil {
glog.V(2).Infof("Failed to update QoS cgroups while syncing pod: %v", err)
}

// Create Mirror Pod for Static Pod if it doesn't already exist
if kubepod.IsStaticPod(pod) {
podFullName := kubecontainer.GetPodFullName(pod)
deleted := false
if mirrorPod != nil {
if mirrorPod.DeletionTimestamp != nil || !kl.podManager.IsMirrorPodOf(mirrorPod, pod) {
// The mirror pod is semantically different from the static pod. Remove
// it. The mirror pod will get recreated later.
glog.Warningf("Deleting mirror pod %q because it is outdated", format.Pod(mirrorPod))
if err := kl.podManager.DeleteMirrorPod(podFullName); err != nil {
glog.Errorf("Failed deleting mirror pod %q: %v", format.Pod(mirrorPod), err)
} else {
deleted = true
}
}
}
if mirrorPod == nil || deleted {
node, err := kl.GetNode()
if err != nil || node.DeletionTimestamp != nil {
glog.V(4).Infof("No need to create a mirror pod, since node %q has been removed from the cluster", kl.nodeName)
} else {
glog.V(4).Infof("Creating a mirror pod for static pod %q", format.Pod(pod))
if err := kl.podManager.CreateMirrorPod(pod); err != nil {
glog.Errorf("Failed creating a mirror pod for %q: %v", format.Pod(pod), err)
}
}
}
}

// Make data directories for the pod
if err := kl.makePodDataDirs(pod); err != nil {
kl.recorder.Eventf(pod, v1.EventTypeWarning, events.FailedToMakePodDataDirectories, "error making pod data directories: %v", err)
glog.Errorf("Unable to make pod data directories for pod %q: %v", format.Pod(pod), err)
return err
}

// makePodDataDirs creates the dirs for the pod datas.
func (kl *Kubelet) makePodDataDirs(pod *v1.Pod) error {
uid := pod.UID
if err := os.MkdirAll(kl.getPodDir(uid), 0750); err != nil && !os.IsExist(err) {
return err
}
if err := os.MkdirAll(kl.getPodVolumesDir(uid), 0750); err != nil && !os.IsExist(err) {
return err
}
if err := os.MkdirAll(kl.getPodPluginsDir(uid), 0750); err != nil && !os.IsExist(err) {
return err
}
return nil
}

// Volume manager will not mount volumes for terminated pods
if !kl.podIsTerminated(pod) {
// Wait for volumes to attach/mount
if err := kl.volumeManager.WaitForAttachAndMount(pod); err != nil {
kl.recorder.Eventf(pod, v1.EventTypeWarning, events.FailedMountVolume, "Unable to mount volumes for pod %q: %v", format.Pod(pod), err)
glog.Errorf("Unable to mount volumes for pod %q: %v; skipping pod", format.Pod(pod), err)
return err
}
}

// Fetch the pull secrets for the pod
pullSecrets := kl.getPullSecretsForPod(pod)

// getPullSecretsForPod inspects the Pod and retrieves the referenced pull
// secrets.
func (kl *Kubelet) getPullSecretsForPod(pod *v1.Pod) []v1.Secret {
pullSecrets := []v1.Secret{}

for _, secretRef := range pod.Spec.ImagePullSecrets {
secret, err := kl.secretManager.GetSecret(pod.Namespace, secretRef.Name)
if err != nil {
glog.Warningf("Unable to retrieve pull secret %s/%s for %s/%s due to %v.The image pull may not succeed.", pod.Namespace, secretRef.Name, pod.Namespace, pod.Name, err)
continue
}

pullSecrets = append(pullSecrets, *secret)
}

return pullSecrets
}

// Call the container runtime's SyncPod callback
result := kl.containerRuntime.SyncPod(pod, apiPodStatus, podStatus, pullSecrets, kl.backOff)
kl.reasonCache.Update(pod.UID, result)
if err := result.Error(); err != nil {
// Do not return error if the only failures were pods in backoff
for _, r := range result.SyncResults {
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 nil
}

// Step 1: Compute sandbox and container changes.
podContainerChanges := m.computePodActions(pod, podStatus)
glog.V(3).Infof("computePodActions got %+v for pod %q", podContainerChanges, format.Pod(pod))
if podContainerChanges.CreateSandbox {
ref, err := ref.GetReference(legacyscheme.Scheme, pod)
if err != nil {
glog.Errorf("Couldn't make a ref to pod %q: '%v'", format.Pod(pod), err)
}
if podContainerChanges.SandboxID != "" {
m.recorder.Eventf(ref, v1.EventTypeNormal, events.SandboxChanged, "Pod sandbox changed, it will be killed and re-created.")
} else {
glog.V(4).Infof("SyncPod received new pod %q, will create a sandbox for it", format.Pod(pod))
}
}

// Step 2: Kill the pod if the sandbox has changed.
if podContainerChanges.KillPod {
if !podContainerChanges.CreateSandbox {
glog.V(4).Infof("Stopping PodSandbox for %q because all other containers are dead.", format.Pod(pod))
} else {
glog.V(4).Infof("Stopping PodSandbox for %q, will start new one", format.Pod(pod))
}

killResult := m.killPodWithSyncResult(pod, kubecontainer.ConvertPodStatusToRunningPod(m.runtimeName, podStatus), nil)
result.AddPodSyncResult(killResult)
if killResult.Error() != nil {
glog.Errorf("killPodWithSyncResult failed: %v", killResult.Error())
return
}

if podContainerChanges.CreateSandbox {
m.purgeInitContainers(pod, podStatus)
}
}

// Step 3: kill any running containers in this pod which are not to keep.
for containerID, containerInfo := range podContainerChanges.ContainersToKill {
glog.V(3).Infof("Killing unwanted container %q(id=%q) for pod %q", containerInfo.name, containerID, format.Pod(pod))
killContainerResult := kubecontainer.NewSyncResult(kubecontainer.KillContainer, containerInfo.name)
result.AddSyncResult(killContainerResult)
if err := m.killContainer(pod, containerID, containerInfo.name, containerInfo.message, nil); err != nil {
killContainerResult.Fail(kubecontainer.ErrKillContainer, err.Error())
glog.Errorf("killContainer %q(id=%q) for pod %q failed: %v", containerInfo.name, containerID, format.Pod(pod), err)
return
}
}

// Step 4: Create a sandbox for the pod if necessary.
...
glog.V(4).Infof("Creating sandbox for pod %q", format.Pod(pod))
createSandboxResult := kubecontainer.NewSyncResult(kubecontainer.CreatePodSandbox, format.Pod(pod))
result.AddSyncResult(createSandboxResult)
podSandboxID, msg, err = m.createPodSandbox(pod, podContainerChanges.Attempt)
if err != nil {
createSandboxResult.Fail(kubecontainer.ErrCreatePodSandbox, msg)
glog.Errorf("createPodSandbox for pod %q failed: %v", format.Pod(pod), err)
ref, referr := ref.GetReference(legacyscheme.Scheme, pod)
if referr != nil {
glog.Errorf("Couldn't make a ref to pod %q: '%v'", format.Pod(pod), referr)
}
m.recorder.Eventf(ref, v1.EventTypeWarning, events.FailedCreatePodSandBox, "Failed create pod sandbox: %v", err)
return
}
glog.V(4).Infof("Created PodSandbox %q for pod %q", podSandboxID, format.Pod(pod))

// Step 5: start the init container.
if container := podContainerChanges.NextInitContainerToStart; container != nil {
// Start the next init container.
startContainerResult := kubecontainer.NewSyncResult(kubecontainer.StartContainer, container.Name)
result.AddSyncResult(startContainerResult)
isInBackOff, msg, err := m.doBackOff(pod, container, podStatus, backOff)
if isInBackOff {
startContainerResult.Fail(err, msg)
glog.V(4).Infof("Backing Off restarting init container %+v in pod %v", container, format.Pod(pod))
return
}

glog.V(4).Infof("Creating init container %+v in pod %v", container, format.Pod(pod))
if msg, err := m.startContainer(podSandboxID, podSandboxConfig, container, pod, podStatus, pullSecrets, podIP, kubecontainer.ContainerTypeInit); err != nil {
startContainerResult.Fail(err, msg)
utilruntime.HandleError(fmt.Errorf("init container start failed: %v: %s", err, msg))
return
}

// Successfully started the container; clear the entry in the failure
glog.V(4).Infof("Completed init container %q for pod %q", container.Name, format.Pod(pod))
}

// Step 6: start containers in podContainerChanges.ContainersToStart.
for _, idx := range podContainerChanges.ContainersToStart {
container := &pod.Spec.Containers[idx]
startContainerResult := kubecontainer.NewSyncResult(kubecontainer.StartContainer, container.Name)
result.AddSyncResult(startContainerResult)

isInBackOff, msg, err := m.doBackOff(pod, container, podStatus, backOff)
if isInBackOff {
startContainerResult.Fail(err, msg)
glog.V(4).Infof("Backing Off restarting container %+v in pod %v", container, format.Pod(pod))
continue
}

glog.V(4).Infof("Creating container %+v in pod %v", container, format.Pod(pod))
if msg, err := m.startContainer(podSandboxID, podSandboxConfig, container, pod, podStatus, pullSecrets, podIP, kubecontainer.ContainerTypeRegular); 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:
glog.V(3).Infof("container start failed: %v: %s", err, msg)
default:
utilruntime.HandleError(fmt.Errorf("container start failed: %v: %s", err, msg))
}
continue
}
}

// startContainer starts a container and returns a message indicates why it is failed on error.
// It starts the container through the following steps:
// * pull the image
// * create the container
// * start the container
// * run the post start lifecycle hooks (if applicable)
func (m *kubeGenericRuntimeManager) startContainer(podSandboxID string, podSandboxConfig *runtimeapi.PodSandboxConfig, container *v1.Container, pod *v1.Pod, podStatus *kubecontainer.PodStatus, pullSecrets []v1.Secret, podIP string, containerType kubecontainer.ContainerType) (string, error) {
...
}

// Step 1: pull the image.
imageRef, msg, err := m.imagePuller.EnsureImageExists(pod, container, pullSecrets)
if err != nil {
m.recordContainerEvent(pod, container, "", v1.EventTypeWarning, events.FailedToCreateContainer, "Error: %v", grpc.ErrorDesc(err))
return msg, err
}

// Step 2: create the container.
ref, err := kubecontainer.GenerateContainerRef(pod, container)
if err != nil {
glog.Errorf("Can't make a ref to pod %q, container %v: %v", format.Pod(pod), container.Name, err)
}
glog.V(4).Infof("Generating ref for container %s: %#v", container.Name, ref)

// For a new container, the RestartCount should be 0
restartCount := 0
containerStatus := podStatus.FindContainerStatusByName(container.Name)
if containerStatus != nil {
restartCount = containerStatus.RestartCount + 1
}

containerConfig, cleanupAction, err := m.generateContainerConfig(container, pod, restartCount, podIP, imageRef, containerType)
if cleanupAction != nil {
defer cleanupAction()
}
if err != nil {
m.recordContainerEvent(pod, container, "", v1.EventTypeWarning, events.FailedToCreateContainer, "Error: %v", grpc.ErrorDesc(err))
return grpc.ErrorDesc(err), ErrCreateContainerConfig
}

containerID, err := m.runtimeService.CreateContainer(podSandboxID, containerConfig, podSandboxConfig)
if err != nil {
m.recordContainerEvent(pod, container, containerID, v1.EventTypeWarning, events.FailedToCreateContainer, "Error: %v", grpc.ErrorDesc(err))
return grpc.ErrorDesc(err), ErrCreateContainer
}
err = m.internalLifecycle.PreStartContainer(pod, container, containerID)
if err != nil {
m.recordContainerEvent(pod, container, containerID, v1.EventTypeWarning, events.FailedToStartContainer, "Internal PreStartContainer hook failed: %v", grpc.ErrorDesc(err))
return grpc.ErrorDesc(err), ErrPreStartHook
}
m.recordContainerEvent(pod, container, containerID, v1.EventTypeNormal, events.CreatedContainer, "Created container")

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 {
m.recordContainerEvent(pod, container, containerID, v1.EventTypeWarning, events.FailedToStartContainer, "Error: %v", grpc.ErrorDesc(err))
return grpc.ErrorDesc(err), kubecontainer.ErrRunContainer
}
m.recordContainerEvent(pod, container, containerID, v1.EventTypeNormal, events.StartedContainer, "Started container")

// 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.
containerMeta := containerConfig.GetMetadata()
sandboxMeta := podSandboxConfig.GetMetadata()
legacySymlink := legacyLogSymlink(containerID, containerMeta.Name, sandboxMeta.Name,
sandboxMeta.Namespace)
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 {
glog.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 {
glog.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)
}
}