上一篇文章中我们已经简单分享过了k8s的各个组件，我们已经知道了pod是由运行在各个node上的kubelet拉起来的，那么这次我们主要从源码(1.10版本)来分析kubelet主要是怎么工作的。
k8s的代码结构比较清晰，如下图所示
我们先看cmd/kubelet/kubelet.go，这个是kubelet的main入口，代码如下：
func main() {
rand.Seed(time.Now().UnixNano())
command := app.NewKubeletCommand()
logs.InitLogs()
defer logs.FlushLogs()
if err := command.Execute(); err != nil {
os.Exit(1)
}
}
在这里我们关心的是RunKubelet的实现
func RunKubelet(kubeServer *options.KubeletServer, kubeDeps *kubelet.Dependencies, runOnce bool) error {
hostname, err := nodeutil.GetHostname(kubeServer.HostnameOverride)
if err != nil {
return err
}
// Query the cloud provider for our node name, default to hostname if kubeDeps.Cloud == nil
nodeName, err := getNodeName(kubeDeps.Cloud, hostname)
if err != nil {
return err
}
// Setup event recorder if required.
makeEventRecorder(kubeDeps, nodeName)
capabilities.Initialize(capabilities.Capabilities{
AllowPrivileged: true,
})
credentialprovider.SetPreferredDockercfgPath(kubeServer.RootDirectory)
klog.V(2).Infof("Using root directory: %v", kubeServer.RootDirectory)
if kubeDeps.OSInterface == nil {
kubeDeps.OSInterface = kubecontainer.RealOS{}
}
k, err := createAndInitKubelet(&kubeServer.KubeletConfiguration,
kubeDeps,
&kubeServer.ContainerRuntimeOptions,
kubeServer.ContainerRuntime,
kubeServer.RuntimeCgroups,
kubeServer.HostnameOverride,
kubeServer.NodeIP,
kubeServer.ProviderID,
kubeServer.CloudProvider,
kubeServer.CertDirectory,
kubeServer.RootDirectory,
kubeServer.RegisterNode,
kubeServer.RegisterWithTaints,
kubeServer.AllowedUnsafeSysctls,
kubeServer.RemoteRuntimeEndpoint,
kubeServer.RemoteImageEndpoint,
kubeServer.ExperimentalMounterPath,
kubeServer.ExperimentalKernelMemcgNotification,
kubeServer.ExperimentalCheckNodeCapabilitiesBeforeMount,
kubeServer.ExperimentalNodeAllocatableIgnoreEvictionThreshold,
kubeServer.MinimumGCAge,
kubeServer.MaxPerPodContainerCount,
kubeServer.MaxContainerCount,
kubeServer.MasterServiceNamespace,
kubeServer.RegisterSchedulable,
kubeServer.NonMasqueradeCIDR,
kubeServer.KeepTerminatedPodVolumes,
kubeServer.NodeLabels,
kubeServer.SeccompProfileRoot,
kubeServer.BootstrapCheckpointPath,
kubeServer.NodeStatusMaxImages)
if err != nil {
return fmt.Errorf("failed to create kubelet: %v", err)
}
// NewMainKubelet should have set up a pod source config if one didn't exist
// when the builder was run. This is just a precaution.
if kubeDeps.PodConfig == nil {
return fmt.Errorf("failed to create kubelet, pod source config was nil")
}
podCfg := kubeDeps.PodConfig
rlimit.RlimitNumFiles(uint64(kubeServer.MaxOpenFiles))
// process pods and exit.
if runOnce {
if _, err := k.RunOnce(podCfg.Updates()); err != nil {
return fmt.Errorf("runonce failed: %v", err)
}
klog.Info("Started kubelet as runonce")
} else {
startKubelet(k, podCfg, &kubeServer.KubeletConfiguration, kubeDeps, kubeServer.EnableCAdvisorJSONEndpoints, kubeServer.EnableServer)
klog.Info("Started kubelet")
}
return nil
}
- createAndInitKubelet，这个方法初始化了一个kubelet的实例，该函数里面调用的makePodSourceConfig颇为值得注意，该函数会调用NewListWatchFromClient(后面会单开文章再写list-watch的实现)，然后监听从apiserver获取的pods更新信息。
- startKubelet，里面最主要的方法是
k.Run(podCfg.Updates())，然后还有一些http的服务，暂时忽略。先说说k.Run，代码实现如下。
// Run starts the kubelet reacting to config updates
func (kl *Kubelet) Run(updates <-chan kubetypes.PodUpdate) {
if kl.logServer == nil {
kl.logServer = http.StripPrefix("/logs/", http.FileServer(http.Dir("/var/log/")))
}
if kl.kubeClient == nil {
klog.Warning("No api server defined - no node status update will be sent.")
}
// Start the cloud provider sync manager
if kl.cloudResourceSyncManager != nil {
go kl.cloudResourceSyncManager.Run(wait.NeverStop)
}
if err := kl.initializeModules(); err != nil {
kl.recorder.Eventf(kl.nodeRef, v1.EventTypeWarning, events.KubeletSetupFailed, err.Error())
klog.Fatal(err)
}
// Start volume manager
go kl.volumeManager.Run(kl.sourcesReady, wait.NeverStop)
if kl.kubeClient != nil {
// Start syncing node status immediately, this may set up things the runtime needs to run.
go wait.Until(kl.syncNodeStatus, kl.nodeStatusUpdateFrequency, wait.NeverStop)
go kl.fastStatusUpdateOnce()
// start syncing lease
if utilfeature.DefaultFeatureGate.Enabled(features.NodeLease) {
go kl.nodeLeaseController.Run(wait.NeverStop)
}
}
go wait.Until(kl.updateRuntimeUp, 5*time.Second, wait.NeverStop)
// Start loop to sync iptables util rules
if kl.makeIPTablesUtilChains {
go wait.Until(kl.syncNetworkUtil, 1*time.Minute, wait.NeverStop)
}
// Start a goroutine responsible for killing pods (that are not properly
// handled by pod workers).
go wait.Until(kl.podKiller, 1*time.Second, wait.NeverStop)
// Start component sync loops.
kl.statusManager.Start()
kl.probeManager.Start()
// Start syncing RuntimeClasses if enabled.
if kl.runtimeClassManager != nil {
kl.runtimeClassManager.Start(wait.NeverStop)
}
// Start the pod lifecycle event generator.
kl.pleg.Start()
kl.syncLoop(updates, kl)
}
在这个方法内，完成的是kubelet的最主要流程。主要包括以下：
- volumeManager，volume相关管理；
- syncNodeStatus，定时同步Node状态；
- fastStatusUpdateOnce，定时检查indexer cache，并且更新相关状态;
- nodeLeaseController，Run 同步租约;
- updateRuntimeUp，定时更新Runtime状态；
- syncNetworkUtil，定时同步网络状态；
- podKiller，定时清理死亡的pod；
- statusManager，pod状态管理；
- probeManager，pod探针管理；
- syncLoop
syncLoop，是这里面的主循环，监听不同channel(http, file, apiserver)的podupdate数据，如果发现有更新，就将pod同步到期望状态。这里面的主要操作是通过syncLoopIteration实现的。代码如下
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 {
klog.Errorf("Update channel is closed. Exiting the sync loop.")
return false
}
switch u.Op {
case kubetypes.ADD:
klog.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:
klog.V(2).Infof("SyncLoop (UPDATE, %q): %q", u.Source, format.PodsWithDeletionTimestamps(u.Pods))
handler.HandlePodUpdates(u.Pods)
case kubetypes.REMOVE:
klog.V(2).Infof("SyncLoop (REMOVE, %q): %q", u.Source, format.Pods(u.Pods))
handler.HandlePodRemoves(u.Pods)
case kubetypes.RECONCILE:
klog.V(4).Infof("SyncLoop (RECONCILE, %q): %q", u.Source, format.Pods(u.Pods))
handler.HandlePodReconcile(u.Pods)
case kubetypes.DELETE:
klog.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:
klog.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?
klog.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 {
klog.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.
klog.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
}
klog.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.
klog.V(4).Infof("SyncLoop (container unhealthy): ignore irrelevant update: %#v", update)
break
}
klog.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.
klog.V(4).Infof("SyncLoop (housekeeping, skipped): sources aren't ready yet.")
} else {
klog.V(4).Infof("SyncLoop (housekeeping)")
if err := handler.HandlePodCleanups(); err != nil {
klog.Errorf("Failed cleaning pods: %v", err)
}
}
}
return true
}
到这里，基本上应该都清楚了。接下来就是调用runtime去做对应的操作。
