kube-scheduler源码解读（1）
Kube Scheduler 组件是Kubernetes中负责决策将Pod具体运行到某个worker节点上的执行者，本系列文章将详细的研读kube-scheduler组件的源码。
本系列文章的源码版本是kubernetes-1.18.2。
本篇文章为系列文章的第一篇，主要分析kube-scheduler组件启动和pod调度的主要流程。
入口函数main
kube-scheduler组件的入口函数main所在的路径为kubernetes-1.18.2/cmd/kube-scheduler/scheduler.go
func main() {
rand.Seed(time.Now().UnixNano())
command := app.NewSchedulerCommand()
// TODO: once we switch everything over to Cobra commands, we can go back to calling
// utilflag.InitFlags() (by removing its pflag.Parse() call). For now, we have to set the
// normalize func and add the go flag set by hand.
pflag.CommandLine.SetNormalizeFunc(cliflag.WordSepNormalizeFunc)
// utilflag.InitFlags()
logs.InitLogs()
defer logs.FlushLogs()
if err := command.Execute(); err != nil {
os.Exit(1)
}
}
入口函数中需要关注的核心点是：
1）command := app.NewSchedulerCommand()
scheduler是一个基于Cobra创建的command line
2）command.Execute()
执行上边定义的命令
schuduler命令的创建函数
NewSchedulerCommand()函数所在的路径为kubernetes-1.18.2/cmd/kube-scheduler/app/server.go
// NewSchedulerCommand creates a *cobra.Command object with default parameters and registryOptions
func NewSchedulerCommand(registryOptions ...Option) *cobra.Command {
opts, err := options.NewOptions()
if err != nil {
klog.Fatalf("unable to initialize command options: %v", err)
}
cmd := &cobra.Command{
Use: "kube-scheduler",
Long: `The Kubernetes scheduler is a policy-rich, topology-aware,
workload-specific function that significantly impacts availability, performance,
and capacity. The scheduler needs to take into account individual and collective
resource requirements, quality of service requirements, hardware/software/policy
constraints, affinity and anti-affinity specifications, data locality, inter-workload
interference, deadlines, and so on. Workload-specific requirements will be exposed
through the API as necessary. See [scheduling](https://kubernetes.io/docs/concepts/scheduling/)
for more information about scheduling and the kube-scheduler component.`,
Run: func(cmd *cobra.Command, args []string) {
if err := runCommand(cmd, args, opts, registryOptions...); err != nil {
fmt.Fprintf(os.Stderr, "%v\n", err)
os.Exit(1)
}
},
}
fs := cmd.Flags()
namedFlagSets := opts.Flags()
verflag.AddFlags(namedFlagSets.FlagSet("global"))
globalflag.AddGlobalFlags(namedFlagSets.FlagSet("global"), cmd.Name())
for _, f := range namedFlagSets.FlagSets {
fs.AddFlagSet(f)
}
usageFmt := "Usage:\n %s\n"
cols, _, _ := term.TerminalSize(cmd.OutOrStdout())
cmd.SetUsageFunc(func(cmd *cobra.Command) error {
fmt.Fprintf(cmd.OutOrStderr(), usageFmt, cmd.UseLine())
cliflag.PrintSections(cmd.OutOrStderr(), namedFlagSets, cols)
return nil
})
cmd.SetHelpFunc(func(cmd *cobra.Command, args []string) {
fmt.Fprintf(cmd.OutOrStdout(), "%s\n\n"+usageFmt, cmd.Long, cmd.UseLine())
cliflag.PrintSections(cmd.OutOrStdout(), namedFlagSets, cols)
})
cmd.MarkFlagFilename("config", "yaml", "yml", "json")
return cmd
}
schuduler命令的创建函数基于cobra首先创建了scheduler command，然后将这个command返回给入口函数main。
而在入口函数main中则通过command.Execute()启动执行了这个command。Execute函数具体执行的是schuduler命令的创建函数设置的Run参数对应的函数。
runCommand函数
runCommand()函数所在的路径为kubernetes-1.18.2/cmd/kube-scheduler/app/server.go
// runCommand runs the scheduler.
func runCommand(cmd *cobra.Command, args []string, opts *options.Options, registryOptions ...Option) error {
verflag.PrintAndExitIfRequested()
utilflag.PrintFlags(cmd.Flags())
if len(args) != 0 {
fmt.Fprint(os.Stderr, "arguments are not supported\n")
}
if errs := opts.Validate(); len(errs) > 0 {
return utilerrors.NewAggregate(errs)
}
if len(opts.WriteConfigTo) > 0 {
c := &schedulerserverconfig.Config{}
if err := opts.ApplyTo(c); err != nil {
return err
}
if err := options.WriteConfigFile(opts.WriteConfigTo, &c.ComponentConfig); err != nil {
return err
}
klog.Infof("Wrote configuration to: %s\n", opts.WriteConfigTo)
return nil
}
c, err := opts.Config()
if err != nil {
return err
}
// Get the completed config
cc := c.Complete()
// Configz registration.
if cz, err := configz.New("componentconfig"); err == nil {
cz.Set(cc.ComponentConfig)
} else {
return fmt.Errorf("unable to register configz: %s", err)
}
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
return Run(ctx, cc, registryOptions...)
}
runCommand函数的主要流程为：
1）验证参数和选项
2）获取config
3）注册config
4）Run函数
Run函数
Run()函数所在的路径为kubernetes-1.18.2/cmd/kube-scheduler/app/server.go
// Run executes the scheduler based on the given configuration. It only returns on error or when context is done.
func Run(ctx context.Context, cc schedulerserverconfig.CompletedConfig, outOfTreeRegistryOptions ...Option) error {
// To help debugging, immediately log version
klog.V(1).Infof("Starting Kubernetes Scheduler version %+v", version.Get())
outOfTreeRegistry := make(framework.Registry)
for _, option := range outOfTreeRegistryOptions {
if err := option(outOfTreeRegistry); err != nil {
return err
}
}
recorderFactory := getRecorderFactory(&cc)
// Create the scheduler.
sched, err := scheduler.New(cc.Client,
cc.InformerFactory,
cc.PodInformer,
recorderFactory,
ctx.Done(),
scheduler.WithProfiles(cc.ComponentConfig.Profiles...),
scheduler.WithAlgorithmSource(cc.ComponentConfig.AlgorithmSource),
scheduler.WithPreemptionDisabled(cc.ComponentConfig.DisablePreemption),
scheduler.WithPercentageOfNodesToScore(cc.ComponentConfig.PercentageOfNodesToScore),
scheduler.WithBindTimeoutSeconds(cc.ComponentConfig.BindTimeoutSeconds),
scheduler.WithFrameworkOutOfTreeRegistry(outOfTreeRegistry),
scheduler.WithPodMaxBackoffSeconds(cc.ComponentConfig.PodMaxBackoffSeconds),
scheduler.WithPodInitialBackoffSeconds(cc.ComponentConfig.PodInitialBackoffSeconds),
scheduler.WithExtenders(cc.ComponentConfig.Extenders...),
)
if err != nil {
return err
}
// Prepare the event broadcaster.
if cc.Broadcaster != nil && cc.EventClient != nil {
cc.Broadcaster.StartRecordingToSink(ctx.Done())
}
if cc.CoreBroadcaster != nil && cc.CoreEventClient != nil {
cc.CoreBroadcaster.StartRecordingToSink(&corev1.EventSinkImpl{Interface: cc.CoreEventClient.Events("")})
}
// Setup healthz checks.
var checks []healthz.HealthChecker
if cc.ComponentConfig.LeaderElection.LeaderElect {
checks = append(checks, cc.LeaderElection.WatchDog)
}
// Start up the healthz server.
if cc.InsecureServing != nil {
separateMetrics := cc.InsecureMetricsServing != nil
handler := buildHandlerChain(newHealthzHandler(&cc.ComponentConfig, separateMetrics, checks...), nil, nil)
if err := cc.InsecureServing.Serve(handler, 0, ctx.Done()); err != nil {
return fmt.Errorf("failed to start healthz server: %v", err)
}
}
if cc.InsecureMetricsServing != nil {
handler := buildHandlerChain(newMetricsHandler(&cc.ComponentConfig), nil, nil)
if err := cc.InsecureMetricsServing.Serve(handler, 0, ctx.Done()); err != nil {
return fmt.Errorf("failed to start metrics server: %v", err)
}
}
if cc.SecureServing != nil {
handler := buildHandlerChain(newHealthzHandler(&cc.ComponentConfig, false, checks...), cc.Authentication.Authenticator, cc.Authorization.Authorizer)
// TODO: handle stoppedCh returned by c.SecureServing.Serve
if _, err := cc.SecureServing.Serve(handler, 0, ctx.Done()); err != nil {
// fail early for secure handlers, removing the old error loop from above
return fmt.Errorf("failed to start secure server: %v", err)
}
}
// Start all informers.
go cc.PodInformer.Informer().Run(ctx.Done())
cc.InformerFactory.Start(ctx.Done())
// Wait for all caches to sync before scheduling.
cc.InformerFactory.WaitForCacheSync(ctx.Done())
// If leader election is enabled, runCommand via LeaderElector until done and exit.
if cc.LeaderElection != nil {
cc.LeaderElection.Callbacks = leaderelection.LeaderCallbacks{
OnStartedLeading: sched.Run,
OnStoppedLeading: func() {
klog.Fatalf("leaderelection lost")
},
}
leaderElector, err := leaderelection.NewLeaderElector(*cc.LeaderElection)
if err != nil {
return fmt.Errorf("couldn't create leader elector: %v", err)
}
leaderElector.Run(ctx)
return fmt.Errorf("lost lease")
}
// Leader election is disabled, so runCommand inline until done.
sched.Run(ctx)
return fmt.Errorf("finished without leader elect")
}
Run函数的主要流程如下：
1）配置相关的插件
2）根据配置创建事件记录器
3）创建scheduler
4）准备事件的广播器
5）配置健康检查机制
6）启动healthz server
7）启动informer
8）根据是否配置了选举机制，来启动scheduler的运行。
sched.Run函数
sched.Run()函数所在的路径为kubernetes-1.18.2/pkg/scheduler/scheduler.go
// Run begins watching and scheduling. It waits for cache to be synced, then starts scheduling and blocked until the context is done.
func (sched *Scheduler) Run(ctx context.Context) {
if !cache.WaitForCacheSync(ctx.Done(), sched.scheduledPodsHasSynced) {
return
}
sched.SchedulingQueue.Run()
wait.UntilWithContext(ctx, sched.scheduleOne, 0)
sched.SchedulingQueue.Close()
}
主要流程为：
1）判断cache是否已经同步
2）Run 函数将pod从podBackoffQ队列移动到activeQ
3）UntilWithContext loops until context is done，此处将会执行scheduleOne函数。
4）Close函数关闭SchedulingQueue
scheduleOne函数
scheduleOne()函数所在的路径为kubernetes-1.18.2/pkg/scheduler/scheduler.go
// scheduleOne does the entire scheduling workflow for a single pod. It is serialized on the scheduling algorithm's host fitting.
func (sched *Scheduler) scheduleOne(ctx context.Context) {
podInfo := sched.NextPod()
// pod could be nil when schedulerQueue is closed
if podInfo == nil || podInfo.Pod == nil {
return
}
pod := podInfo.Pod
prof, err := sched.profileForPod(pod)
if err != nil {
// This shouldn't happen, because we only accept for scheduling the pods
// which specify a scheduler name that matches one of the profiles.
klog.Error(err)
return
}
if sched.skipPodSchedule(prof, pod) {
return
}
klog.V(3).Infof("Attempting to schedule pod: %v/%v", pod.Namespace, pod.Name)
// Synchronously attempt to find a fit for the pod.
start := time.Now()
state := framework.NewCycleState()
state.SetRecordPluginMetrics(rand.Intn(100) < pluginMetricsSamplePercent)
schedulingCycleCtx, cancel := context.WithCancel(ctx)
defer cancel()
scheduleResult, err := sched.Algorithm.Schedule(schedulingCycleCtx, prof, state, pod)
if err != nil {
// Schedule() may have failed because the pod would not fit on any host, so we try to
// preempt, with the expectation that the next time the pod is tried for scheduling it
// will fit due to the preemption. It is also possible that a different pod will schedule
// into the resources that were preempted, but this is harmless.
if fitError, ok := err.(*core.FitError); ok {
if sched.DisablePreemption {
klog.V(3).Infof("Pod priority feature is not enabled or preemption is disabled by scheduler configuration." +
" No preemption is performed.")
} else {
preemptionStartTime := time.Now()
sched.preempt(schedulingCycleCtx, prof, state, pod, fitError)
metrics.PreemptionAttempts.Inc()
metrics.SchedulingAlgorithmPreemptionEvaluationDuration.Observe(metrics.SinceInSeconds(preemptionStartTime))
metrics.DeprecatedSchedulingDuration.WithLabelValues(metrics.PreemptionEvaluation).Observe(metrics.SinceInSeconds(preemptionStartTime))
}
// Pod did not fit anywhere, so it is counted as a failure. If preemption
// succeeds, the pod should get counted as a success the next time we try to
// schedule it. (hopefully)
metrics.PodScheduleFailures.Inc()
} else {
klog.Errorf("error selecting node for pod: %v", err)
metrics.PodScheduleErrors.Inc()
}
sched.recordSchedulingFailure(prof, podInfo.DeepCopy(), err, v1.PodReasonUnschedulable, err.Error())
return
}
metrics.SchedulingAlgorithmLatency.Observe(metrics.SinceInSeconds(start))
// Tell the cache to assume that a pod now is running on a given node, even though it hasn't been bound yet.
// This allows us to keep scheduling without waiting on binding to occur.
assumedPodInfo := podInfo.DeepCopy()
assumedPod := assumedPodInfo.Pod
// Assume volumes first before assuming the pod.
//
// If all volumes are completely bound, then allBound is true and binding will be skipped.
//
// Otherwise, binding of volumes is started after the pod is assumed, but before pod binding.
//
// This function modifies 'assumedPod' if volume binding is required.
allBound, err := sched.VolumeBinder.AssumePodVolumes(assumedPod, scheduleResult.SuggestedHost)
if err != nil {
sched.recordSchedulingFailure(prof, assumedPodInfo, err, SchedulerError,
fmt.Sprintf("AssumePodVolumes failed: %v", err))
metrics.PodScheduleErrors.Inc()
return
}
// Run "reserve" plugins.
if sts := prof.RunReservePlugins(schedulingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost); !sts.IsSuccess() {
sched.recordSchedulingFailure(prof, assumedPodInfo, sts.AsError(), SchedulerError, sts.Message())
metrics.PodScheduleErrors.Inc()
return
}
// assume modifies `assumedPod` by setting NodeName=scheduleResult.SuggestedHost
err = sched.assume(assumedPod, scheduleResult.SuggestedHost)
if err != nil {
// This is most probably result of a BUG in retrying logic.
// We report an error here so that pod scheduling can be retried.
// This relies on the fact that Error will check if the pod has been bound
// to a node and if so will not add it back to the unscheduled pods queue
// (otherwise this would cause an infinite loop).
sched.recordSchedulingFailure(prof, assumedPodInfo, err, SchedulerError, fmt.Sprintf("AssumePod failed: %v", err))
metrics.PodScheduleErrors.Inc()
// trigger un-reserve plugins to clean up state associated with the reserved Pod
prof.RunUnreservePlugins(schedulingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)
return
}
// Run "permit" plugins.
runPermitStatus := prof.RunPermitPlugins(schedulingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)
if runPermitStatus.Code() != framework.Wait && !runPermitStatus.IsSuccess() {
var reason string
if runPermitStatus.IsUnschedulable() {
metrics.PodScheduleFailures.Inc()
reason = v1.PodReasonUnschedulable
} else {
metrics.PodScheduleErrors.Inc()
reason = SchedulerError
}
if forgetErr := sched.Cache().ForgetPod(assumedPod); forgetErr != nil {
klog.Errorf("scheduler cache ForgetPod failed: %v", forgetErr)
}
// One of the plugins returned status different than success or wait.
prof.RunUnreservePlugins(schedulingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)
sched.recordSchedulingFailure(prof, assumedPodInfo, runPermitStatus.AsError(), reason, runPermitStatus.Message())
return
}
// bind the pod to its host asynchronously (we can do this b/c of the assumption step above).
go func() {
bindingCycleCtx, cancel := context.WithCancel(ctx)
defer cancel()
metrics.SchedulerGoroutines.WithLabelValues("binding").Inc()
defer metrics.SchedulerGoroutines.WithLabelValues("binding").Dec()
waitOnPermitStatus := prof.WaitOnPermit(bindingCycleCtx, assumedPod)
if !waitOnPermitStatus.IsSuccess() {
var reason string
if waitOnPermitStatus.IsUnschedulable() {
metrics.PodScheduleFailures.Inc()
reason = v1.PodReasonUnschedulable
} else {
metrics.PodScheduleErrors.Inc()
reason = SchedulerError
}
if forgetErr := sched.Cache().ForgetPod(assumedPod); forgetErr != nil {
klog.Errorf("scheduler cache ForgetPod failed: %v", forgetErr)
}
// trigger un-reserve plugins to clean up state associated with the reserved Pod
prof.RunUnreservePlugins(bindingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)
sched.recordSchedulingFailure(prof, assumedPodInfo, waitOnPermitStatus.AsError(), reason, waitOnPermitStatus.Message())
return
}
// Bind volumes first before Pod
if !allBound {
err := sched.bindVolumes(assumedPod)
if err != nil {
sched.recordSchedulingFailure(prof, assumedPodInfo, err, "VolumeBindingFailed", err.Error())
metrics.PodScheduleErrors.Inc()
// trigger un-reserve plugins to clean up state associated with the reserved Pod
prof.RunUnreservePlugins(bindingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)
return
}
}
// Run "prebind" plugins.
preBindStatus := prof.RunPreBindPlugins(bindingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)
if !preBindStatus.IsSuccess() {
var reason string
metrics.PodScheduleErrors.Inc()
reason = SchedulerError
if forgetErr := sched.Cache().ForgetPod(assumedPod); forgetErr != nil {
klog.Errorf("scheduler cache ForgetPod failed: %v", forgetErr)
}
// trigger un-reserve plugins to clean up state associated with the reserved Pod
prof.RunUnreservePlugins(bindingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)
sched.recordSchedulingFailure(prof, assumedPodInfo, preBindStatus.AsError(), reason, preBindStatus.Message())
return
}
err := sched.bind(bindingCycleCtx, prof, assumedPod, scheduleResult.SuggestedHost, state)
metrics.E2eSchedulingLatency.Observe(metrics.SinceInSeconds(start))
if err != nil {
metrics.PodScheduleErrors.Inc()
// trigger un-reserve plugins to clean up state associated with the reserved Pod
prof.RunUnreservePlugins(bindingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)
sched.recordSchedulingFailure(prof, assumedPodInfo, err, SchedulerError, fmt.Sprintf("Binding rejected: %v", err))
} else {
// Calculating nodeResourceString can be heavy. Avoid it if klog verbosity is below 2.
if klog.V(2) {
klog.Infof("pod %v/%v is bound successfully on node %q, %d nodes evaluated, %d nodes were found feasible.", assumedPod.Namespace, assumedPod.Name, scheduleResult.SuggestedHost, scheduleResult.EvaluatedNodes, scheduleResult.FeasibleNodes)
}
metrics.PodScheduleSuccesses.Inc()
metrics.PodSchedulingAttempts.Observe(float64(podInfo.Attempts))
metrics.PodSchedulingDuration.Observe(metrics.SinceInSeconds(podInfo.InitialAttemptTimestamp))
// Run "postbind" plugins.
prof.RunPostBindPlugins(bindingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)
}
}()
}
scheduleOne函数的主要流程如下：
1）从未调度的Pod中获取一个pod
2）根据配置的调度算法为整个pod选择一个合适的host，如果调度成功继续执行，如果不成功的话，会根据是否设置了抢占调度机制来执行抢占调度策略。
3）Volume，reserve plugin，permit plugin等的检查验证
4）更新pod的NodeName=scheduleResult.SuggestedHost
5）异步执行将pod和host进行绑定
总结
至此，scheduler组件的启动流程和pod的主要调度流程分析结束了，接下来worker节点上的kubelet组件监听到有新的调度到本节点的pod，就会执行pod的创建流程。
本篇文章只是简单的分析了scheduler的的主要流程，接下来的文章中将对每一个流程进行详细的分析解读。