k3s/vendor/k8s.io/kubernetes/cmd/kube-scheduler/app/server.go

/*
Copyright 2014 The Kubernetes Authors.

Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at

    http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
*/

// Package app implements a Server object for running the scheduler.
package app

import (
	"context"
	"fmt"
	"net/http"
	"os"
	goruntime "runtime"

	"github.com/spf13/cobra"

	utilerrors "k8s.io/apimachinery/pkg/util/errors"
	"k8s.io/apiserver/pkg/authentication/authenticator"
	"k8s.io/apiserver/pkg/authorization/authorizer"
	genericapifilters "k8s.io/apiserver/pkg/endpoints/filters"
	apirequest "k8s.io/apiserver/pkg/endpoints/request"
	genericfilters "k8s.io/apiserver/pkg/server/filters"
	"k8s.io/apiserver/pkg/server/healthz"
	"k8s.io/apiserver/pkg/server/mux"
	"k8s.io/apiserver/pkg/server/routes"
	"k8s.io/client-go/informers"
	"k8s.io/client-go/kubernetes/scheme"
	"k8s.io/client-go/tools/events"
	"k8s.io/client-go/tools/leaderelection"
	cliflag "k8s.io/component-base/cli/flag"
	"k8s.io/component-base/cli/globalflag"
	"k8s.io/component-base/configz"
	"k8s.io/component-base/logs"
	"k8s.io/component-base/metrics/legacyregistry"
	"k8s.io/component-base/term"
	"k8s.io/component-base/version"
	"k8s.io/component-base/version/verflag"
	"k8s.io/klog/v2"
	schedulerserverconfig "k8s.io/kubernetes/cmd/kube-scheduler/app/config"
	"k8s.io/kubernetes/cmd/kube-scheduler/app/options"
	"k8s.io/kubernetes/pkg/scheduler"
	kubeschedulerconfig "k8s.io/kubernetes/pkg/scheduler/apis/config"
	"k8s.io/kubernetes/pkg/scheduler/framework/runtime"
	"k8s.io/kubernetes/pkg/scheduler/metrics/resources"
	"k8s.io/kubernetes/pkg/scheduler/profile"
)

// Option configures a framework.Registry.
type Option func(runtime.Registry) error

// 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 control plane process which assigns
Pods to Nodes. The scheduler determines which Nodes are valid placements for
each Pod in the scheduling queue according to constraints and available
resources. The scheduler then ranks each valid Node and binds the Pod to a
suitable Node. Multiple different schedulers may be used within a cluster;
kube-scheduler is the reference implementation.
See [scheduling](https://kubernetes.io/docs/concepts/scheduling-eviction/)
for more information about scheduling and the kube-scheduler component.`,
		Run: func(cmd *cobra.Command, args []string) {
			if err := runCommand(cmd, opts, registryOptions...); err != nil {
				fmt.Fprintf(os.Stderr, "%v\n", err)
				os.Exit(1)
			}
		},
		Args: func(cmd *cobra.Command, args []string) error {
			for _, arg := range args {
				if len(arg) > 0 {
					return fmt.Errorf("%q does not take any arguments, got %q", cmd.CommandPath(), args)
				}
			}
			return nil
		},
	}
	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
}

// runCommand runs the scheduler.
func runCommand(cmd *cobra.Command, opts *options.Options, registryOptions ...Option) error {
	verflag.PrintAndExitIfRequested()
	cliflag.PrintFlags(cmd.Flags())

	ctx, cancel := context.WithCancel(context.Background())
	defer cancel()

	cc, sched, err := Setup(ctx, opts, registryOptions...)
	if err != nil {
		return err
	}

	return Run(ctx, cc, sched)
}

// 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, sched *scheduler.Scheduler) error {
	// To help debugging, immediately log version
	klog.V(1).Infof("Starting Kubernetes Scheduler version %+v", version.Get())

	// Configz registration.
	if cz, err := configz.New("componentconfig"); err == nil {
		cz.Set(cc.ComponentConfig)
	} else {
		return fmt.Errorf("unable to register configz: %s", err)
	}

	// Prepare the event broadcaster.
	cc.EventBroadcaster.StartRecordingToSink(ctx.Done())

	// Setup healthz checks.
	var checks []healthz.HealthChecker
	if cc.ComponentConfig.LeaderElection.LeaderElect {
		checks = append(checks, cc.LeaderElection.WatchDog)
	}

	waitingForLeader := make(chan struct{})
	isLeader := func() bool {
		select {
		case _, ok := <-waitingForLeader:
			// if channel is closed, we are leading
			return !ok
		default:
			// channel is open, we are waiting for a leader
			return false
		}
	}

	// Start up the healthz server.
	if cc.InsecureServing != nil {
		separateMetrics := cc.InsecureMetricsServing != nil
		handler := buildHandlerChain(newHealthzHandler(&cc.ComponentConfig, cc.InformerFactory, isLeader, 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, cc.InformerFactory, isLeader), 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, cc.InformerFactory, isLeader, 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.
	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: func(ctx context.Context) {
				close(waitingForLeader)
				sched.Run(ctx)
			},
			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.
	close(waitingForLeader)
	sched.Run(ctx)
	return fmt.Errorf("finished without leader elect")
}

// buildHandlerChain wraps the given handler with the standard filters.
func buildHandlerChain(handler http.Handler, authn authenticator.Request, authz authorizer.Authorizer) http.Handler {
	requestInfoResolver := &apirequest.RequestInfoFactory{}
	failedHandler := genericapifilters.Unauthorized(scheme.Codecs)

	handler = genericapifilters.WithAuthorization(handler, authz, scheme.Codecs)
	handler = genericapifilters.WithAuthentication(handler, authn, failedHandler, nil)
	handler = genericapifilters.WithRequestInfo(handler, requestInfoResolver)
	handler = genericapifilters.WithCacheControl(handler)
	handler = genericfilters.WithPanicRecovery(handler, requestInfoResolver)

	return handler
}

func installMetricHandler(pathRecorderMux *mux.PathRecorderMux, informers informers.SharedInformerFactory, isLeader func() bool) {
	configz.InstallHandler(pathRecorderMux)
	pathRecorderMux.Handle("/metrics", legacyregistry.HandlerWithReset())

	resourceMetricsHandler := resources.Handler(informers.Core().V1().Pods().Lister())
	pathRecorderMux.HandleFunc("/metrics/resources", func(w http.ResponseWriter, req *http.Request) {
		if !isLeader() {
			return
		}
		resourceMetricsHandler.ServeHTTP(w, req)
	})
}

// newMetricsHandler builds a metrics server from the config.
func newMetricsHandler(config *kubeschedulerconfig.KubeSchedulerConfiguration, informers informers.SharedInformerFactory, isLeader func() bool) http.Handler {
	pathRecorderMux := mux.NewPathRecorderMux("kube-scheduler")
	installMetricHandler(pathRecorderMux, informers, isLeader)
	if config.EnableProfiling {
		routes.Profiling{}.Install(pathRecorderMux)
		if config.EnableContentionProfiling {
			goruntime.SetBlockProfileRate(1)
		}
		routes.DebugFlags{}.Install(pathRecorderMux, "v", routes.StringFlagPutHandler(logs.GlogSetter))
	}
	return pathRecorderMux
}

// newHealthzHandler creates a healthz server from the config, and will also
// embed the metrics handler if the healthz and metrics address configurations
// are the same.
func newHealthzHandler(config *kubeschedulerconfig.KubeSchedulerConfiguration, informers informers.SharedInformerFactory, isLeader func() bool, separateMetrics bool, checks ...healthz.HealthChecker) http.Handler {
	pathRecorderMux := mux.NewPathRecorderMux("kube-scheduler")
	healthz.InstallHandler(pathRecorderMux, checks...)
	if !separateMetrics {
		installMetricHandler(pathRecorderMux, informers, isLeader)
	}
	if config.EnableProfiling {
		routes.Profiling{}.Install(pathRecorderMux)
		if config.EnableContentionProfiling {
			goruntime.SetBlockProfileRate(1)
		}
		routes.DebugFlags{}.Install(pathRecorderMux, "v", routes.StringFlagPutHandler(logs.GlogSetter))
	}
	return pathRecorderMux
}

func getRecorderFactory(cc *schedulerserverconfig.CompletedConfig) profile.RecorderFactory {
	return func(name string) events.EventRecorder {
		return cc.EventBroadcaster.NewRecorder(name)
	}
}

// WithPlugin creates an Option based on plugin name and factory. Please don't remove this function: it is used to register out-of-tree plugins,
// hence there are no references to it from the kubernetes scheduler code base.
func WithPlugin(name string, factory runtime.PluginFactory) Option {
	return func(registry runtime.Registry) error {
		return registry.Register(name, factory)
	}
}

// Setup creates a completed config and a scheduler based on the command args and options
func Setup(ctx context.Context, opts *options.Options, outOfTreeRegistryOptions ...Option) (*schedulerserverconfig.CompletedConfig, *scheduler.Scheduler, error) {
	if errs := opts.Validate(); len(errs) > 0 {
		return nil, nil, utilerrors.NewAggregate(errs)
	}

	c, err := opts.Config()
	if err != nil {
		return nil, nil, err
	}

	// Get the completed config
	cc := c.Complete()

	outOfTreeRegistry := make(runtime.Registry)
	for _, option := range outOfTreeRegistryOptions {
		if err := option(outOfTreeRegistry); err != nil {
			return nil, nil, err
		}
	}

	recorderFactory := getRecorderFactory(&cc)
	completedProfiles := make([]kubeschedulerconfig.KubeSchedulerProfile, 0)
	// Create the scheduler.
	sched, err := scheduler.New(cc.Client,
		cc.InformerFactory,
		recorderFactory,
		ctx.Done(),
		scheduler.WithProfiles(cc.ComponentConfig.Profiles...),
		scheduler.WithAlgorithmSource(cc.ComponentConfig.AlgorithmSource),
		scheduler.WithPercentageOfNodesToScore(cc.ComponentConfig.PercentageOfNodesToScore),
		scheduler.WithFrameworkOutOfTreeRegistry(outOfTreeRegistry),
		scheduler.WithPodMaxBackoffSeconds(cc.ComponentConfig.PodMaxBackoffSeconds),
		scheduler.WithPodInitialBackoffSeconds(cc.ComponentConfig.PodInitialBackoffSeconds),
		scheduler.WithExtenders(cc.ComponentConfig.Extenders...),
		scheduler.WithParallelism(cc.ComponentConfig.Parallelism),
		scheduler.WithBuildFrameworkCapturer(func(profile kubeschedulerconfig.KubeSchedulerProfile) {
			// Profiles are processed during Framework instantiation to set default plugins and configurations. Capturing them for logging
			completedProfiles = append(completedProfiles, profile)
		}),
	)
	if err != nil {
		return nil, nil, err
	}
	if err := options.LogOrWriteConfig(opts.WriteConfigTo, &cc.ComponentConfig, completedProfiles); err != nil {
		return nil, nil, err
	}

	return &cc, sched, nil
}