kubernetes/pkg/scheduler/scheduler.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 scheduler

import (
	"context"
	"fmt"
	"math/rand"
	"strconv"
	"sync"
	"sync/atomic"
	"time"

	v1 "k8s.io/api/core/v1"
	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
	utilruntime "k8s.io/apimachinery/pkg/util/runtime"
	"k8s.io/apimachinery/pkg/util/sets"
	"k8s.io/apimachinery/pkg/util/wait"
	"k8s.io/client-go/dynamic/dynamicinformer"
	"k8s.io/client-go/informers"
	coreinformers "k8s.io/client-go/informers/core/v1"
	clientset "k8s.io/client-go/kubernetes"
	restclient "k8s.io/client-go/rest"
	"k8s.io/client-go/tools/cache"
	"k8s.io/klog/v2"
	"k8s.io/kube-scheduler/config/v1beta3"
	extenderv1 "k8s.io/kube-scheduler/extender/v1"
	podutil "k8s.io/kubernetes/pkg/api/v1/pod"
	"k8s.io/kubernetes/pkg/apis/core/validation"
	"k8s.io/kubernetes/pkg/scheduler/apis/config"
	schedulerapi "k8s.io/kubernetes/pkg/scheduler/apis/config"
	"k8s.io/kubernetes/pkg/scheduler/apis/config/scheme"
	"k8s.io/kubernetes/pkg/scheduler/framework"
	"k8s.io/kubernetes/pkg/scheduler/framework/parallelize"
	frameworkplugins "k8s.io/kubernetes/pkg/scheduler/framework/plugins"
	frameworkruntime "k8s.io/kubernetes/pkg/scheduler/framework/runtime"
	internalcache "k8s.io/kubernetes/pkg/scheduler/internal/cache"
	internalqueue "k8s.io/kubernetes/pkg/scheduler/internal/queue"
	"k8s.io/kubernetes/pkg/scheduler/metrics"
	"k8s.io/kubernetes/pkg/scheduler/profile"
	"k8s.io/kubernetes/pkg/scheduler/util"
	utiltrace "k8s.io/utils/trace"
)

const (
	// SchedulerError is the reason recorded for events when an error occurs during scheduling a pod.
	SchedulerError = "SchedulerError"
	// Percentage of plugin metrics to be sampled.
	pluginMetricsSamplePercent = 10
	// Duration the scheduler will wait before expiring an assumed pod.
	// See issue #106361 for more details about this parameter and its value.
	durationToExpireAssumedPod = 15 * time.Minute
	// minFeasibleNodesToFind is the minimum number of nodes that would be scored
	// in each scheduling cycle. This is a semi-arbitrary value to ensure that a
	// certain minimum of nodes are checked for feasibility. This in turn helps
	// ensure a minimum level of spreading.
	minFeasibleNodesToFind = 100
	// minFeasibleNodesPercentageToFind is the minimum percentage of nodes that
	// would be scored in each scheduling cycle. This is a semi-arbitrary value
	// to ensure that a certain minimum of nodes are checked for feasibility.
	// This in turn helps ensure a minimum level of spreading.
	minFeasibleNodesPercentageToFind = 5
)

// ErrNoNodesAvailable is used to describe the error that no nodes available to schedule pods.
var ErrNoNodesAvailable = fmt.Errorf("no nodes available to schedule pods")

// Scheduler watches for new unscheduled pods. It attempts to find
// nodes that they fit on and writes bindings back to the api server.
type Scheduler struct {
	// It is expected that changes made via Cache will be observed
	// by NodeLister and Algorithm.
	Cache internalcache.Cache

	Extenders []framework.Extender

	// NextPod should be a function that blocks until the next pod
	// is available. We don't use a channel for this, because scheduling
	// a pod may take some amount of time and we don't want pods to get
	// stale while they sit in a channel.
	NextPod func() *framework.QueuedPodInfo

	// Error is called if there is an error. It is passed the pod in
	// question, and the error
	Error func(*framework.QueuedPodInfo, error)

	// SchedulePod tries to schedule the given pod to one of the nodes in the node list.
	// Return a struct of ScheduleResult with the name of suggested host on success,
	// otherwise will return a FitError with reasons.
	SchedulePod func(ctx context.Context, fwk framework.Framework, state *framework.CycleState, pod *v1.Pod) (ScheduleResult, error)

	// Close this to shut down the scheduler.
	StopEverything <-chan struct{}

	// SchedulingQueue holds pods to be scheduled
	SchedulingQueue internalqueue.SchedulingQueue

	// Profiles are the scheduling profiles.
	Profiles profile.Map

	client clientset.Interface

	nodeInfoSnapshot *internalcache.Snapshot

	percentageOfNodesToScore int32

	nextStartNodeIndex int
}

type schedulerOptions struct {
	componentConfigVersion       string
	kubeConfig                   *restclient.Config
	percentageOfNodesToScore     int32
	podInitialBackoffSeconds     int64
	podMaxBackoffSeconds         int64
	podMaxUnschedulableQDuration time.Duration
	// Contains out-of-tree plugins to be merged with the in-tree registry.
	frameworkOutOfTreeRegistry frameworkruntime.Registry
	profiles                   []schedulerapi.KubeSchedulerProfile
	extenders                  []schedulerapi.Extender
	frameworkCapturer          FrameworkCapturer
	parallelism                int32
	applyDefaultProfile        bool
}

// Option configures a Scheduler
type Option func(*schedulerOptions)

// ScheduleResult represents the result of one pod scheduled. It will contain
// the final selected Node, along with the selected intermediate information.
type ScheduleResult struct {
	// Name of the scheduler suggest host
	SuggestedHost string
	// Number of nodes scheduler evaluated on one pod scheduled
	EvaluatedNodes int
	// Number of feasible nodes on one pod scheduled
	FeasibleNodes int
}

// WithComponentConfigVersion sets the component config version to the
// KubeSchedulerConfiguration version used. The string should be the full
// scheme group/version of the external type we converted from (for example
// "kubescheduler.config.k8s.io/v1beta2")
func WithComponentConfigVersion(apiVersion string) Option {
	return func(o *schedulerOptions) {
		o.componentConfigVersion = apiVersion
	}
}

// WithKubeConfig sets the kube config for Scheduler.
func WithKubeConfig(cfg *restclient.Config) Option {
	return func(o *schedulerOptions) {
		o.kubeConfig = cfg
	}
}

// WithProfiles sets profiles for Scheduler. By default, there is one profile
// with the name "default-scheduler".
func WithProfiles(p ...schedulerapi.KubeSchedulerProfile) Option {
	return func(o *schedulerOptions) {
		o.profiles = p
		o.applyDefaultProfile = false
	}
}

// WithParallelism sets the parallelism for all scheduler algorithms. Default is 16.
func WithParallelism(threads int32) Option {
	return func(o *schedulerOptions) {
		o.parallelism = threads
	}
}

// WithPercentageOfNodesToScore sets percentageOfNodesToScore for Scheduler, the default value is 50
func WithPercentageOfNodesToScore(percentageOfNodesToScore int32) Option {
	return func(o *schedulerOptions) {
		o.percentageOfNodesToScore = percentageOfNodesToScore
	}
}

// WithFrameworkOutOfTreeRegistry sets the registry for out-of-tree plugins. Those plugins
// will be appended to the default registry.
func WithFrameworkOutOfTreeRegistry(registry frameworkruntime.Registry) Option {
	return func(o *schedulerOptions) {
		o.frameworkOutOfTreeRegistry = registry
	}
}

// WithPodInitialBackoffSeconds sets podInitialBackoffSeconds for Scheduler, the default value is 1
func WithPodInitialBackoffSeconds(podInitialBackoffSeconds int64) Option {
	return func(o *schedulerOptions) {
		o.podInitialBackoffSeconds = podInitialBackoffSeconds
	}
}

// WithPodMaxBackoffSeconds sets podMaxBackoffSeconds for Scheduler, the default value is 10
func WithPodMaxBackoffSeconds(podMaxBackoffSeconds int64) Option {
	return func(o *schedulerOptions) {
		o.podMaxBackoffSeconds = podMaxBackoffSeconds
	}
}

// WithPodMaxUnschedulableQDuration sets PodMaxUnschedulableQDuration for PriorityQueue.
func WithPodMaxUnschedulableQDuration(duration time.Duration) Option {
	return func(o *schedulerOptions) {
		o.podMaxUnschedulableQDuration = duration
	}
}

// WithExtenders sets extenders for the Scheduler
func WithExtenders(e ...schedulerapi.Extender) Option {
	return func(o *schedulerOptions) {
		o.extenders = e
	}
}

// FrameworkCapturer is used for registering a notify function in building framework.
type FrameworkCapturer func(schedulerapi.KubeSchedulerProfile)

// WithBuildFrameworkCapturer sets a notify function for getting buildFramework details.
func WithBuildFrameworkCapturer(fc FrameworkCapturer) Option {
	return func(o *schedulerOptions) {
		o.frameworkCapturer = fc
	}
}

var defaultSchedulerOptions = schedulerOptions{
	percentageOfNodesToScore:     schedulerapi.DefaultPercentageOfNodesToScore,
	podInitialBackoffSeconds:     int64(internalqueue.DefaultPodInitialBackoffDuration.Seconds()),
	podMaxBackoffSeconds:         int64(internalqueue.DefaultPodMaxBackoffDuration.Seconds()),
	podMaxUnschedulableQDuration: internalqueue.DefaultPodMaxUnschedulableQDuration,
	parallelism:                  int32(parallelize.DefaultParallelism),
	// Ideally we would statically set the default profile here, but we can't because
	// creating the default profile may require testing feature gates, which may get
	// set dynamically in tests. Therefore, we delay creating it until New is actually
	// invoked.
	applyDefaultProfile: true,
}

// newScheduler creates a Scheduler object.
func newScheduler(
	cache internalcache.Cache,
	extenders []framework.Extender,
	nextPod func() *framework.QueuedPodInfo,
	Error func(*framework.QueuedPodInfo, error),
	stopEverything <-chan struct{},
	schedulingQueue internalqueue.SchedulingQueue,
	profiles profile.Map,
	client clientset.Interface,
	nodeInfoSnapshot *internalcache.Snapshot,
	percentageOfNodesToScore int32) *Scheduler {
	sched := Scheduler{
		Cache:                    cache,
		Extenders:                extenders,
		NextPod:                  nextPod,
		Error:                    Error,
		StopEverything:           stopEverything,
		SchedulingQueue:          schedulingQueue,
		Profiles:                 profiles,
		client:                   client,
		nodeInfoSnapshot:         nodeInfoSnapshot,
		percentageOfNodesToScore: percentageOfNodesToScore,
	}
	sched.SchedulePod = sched.schedulePod
	return &sched
}

// New returns a Scheduler
func New(client clientset.Interface,
	informerFactory informers.SharedInformerFactory,
	dynInformerFactory dynamicinformer.DynamicSharedInformerFactory,
	recorderFactory profile.RecorderFactory,
	stopCh <-chan struct{},
	opts ...Option) (*Scheduler, error) {

	stopEverything := stopCh
	if stopEverything == nil {
		stopEverything = wait.NeverStop
	}

	options := defaultSchedulerOptions
	for _, opt := range opts {
		opt(&options)
	}

	if options.applyDefaultProfile {
		var versionedCfg v1beta3.KubeSchedulerConfiguration
		scheme.Scheme.Default(&versionedCfg)
		cfg := config.KubeSchedulerConfiguration{}
		if err := scheme.Scheme.Convert(&versionedCfg, &cfg, nil); err != nil {
			return nil, err
		}
		options.profiles = cfg.Profiles
	}
	schedulerCache := internalcache.New(durationToExpireAssumedPod, stopEverything)

	registry := frameworkplugins.NewInTreeRegistry()
	if err := registry.Merge(options.frameworkOutOfTreeRegistry); err != nil {
		return nil, err
	}

	snapshot := internalcache.NewEmptySnapshot()
	clusterEventMap := make(map[framework.ClusterEvent]sets.String)

	configurator := &Configurator{
		componentConfigVersion:       options.componentConfigVersion,
		client:                       client,
		kubeConfig:                   options.kubeConfig,
		recorderFactory:              recorderFactory,
		informerFactory:              informerFactory,
		schedulerCache:               schedulerCache,
		StopEverything:               stopEverything,
		percentageOfNodesToScore:     options.percentageOfNodesToScore,
		podInitialBackoffSeconds:     options.podInitialBackoffSeconds,
		podMaxBackoffSeconds:         options.podMaxBackoffSeconds,
		podMaxUnschedulableQDuration: options.podMaxUnschedulableQDuration,
		profiles:                     append([]schedulerapi.KubeSchedulerProfile(nil), options.profiles...),
		registry:                     registry,
		nodeInfoSnapshot:             snapshot,
		extenders:                    options.extenders,
		frameworkCapturer:            options.frameworkCapturer,
		parallellism:                 options.parallelism,
		clusterEventMap:              clusterEventMap,
	}

	metrics.Register()

	// Create the config from component config
	sched, err := configurator.create()
	if err != nil {
		return nil, fmt.Errorf("couldn't create scheduler: %v", err)
	}

	addAllEventHandlers(sched, informerFactory, dynInformerFactory, unionedGVKs(clusterEventMap))

	return sched, nil
}

func unionedGVKs(m map[framework.ClusterEvent]sets.String) map[framework.GVK]framework.ActionType {
	gvkMap := make(map[framework.GVK]framework.ActionType)
	for evt := range m {
		if _, ok := gvkMap[evt.Resource]; ok {
			gvkMap[evt.Resource] |= evt.ActionType
		} else {
			gvkMap[evt.Resource] = evt.ActionType
		}
	}
	return gvkMap
}

// Run begins watching and scheduling. It starts scheduling and blocked until the context is done.
func (sched *Scheduler) Run(ctx context.Context) {
	sched.SchedulingQueue.Run()
	wait.UntilWithContext(ctx, sched.scheduleOne, 0)
	sched.SchedulingQueue.Close()
}

// handleSchedulingFailure records an event for the pod that indicates the
// pod has failed to schedule. Also, update the pod condition and nominated node name if set.
func (sched *Scheduler) handleSchedulingFailure(fwk framework.Framework, podInfo *framework.QueuedPodInfo, err error, reason string, nominatingInfo *framework.NominatingInfo) {
	sched.Error(podInfo, err)

	// Update the scheduling queue with the nominated pod information. Without
	// this, there would be a race condition between the next scheduling cycle
	// and the time the scheduler receives a Pod Update for the nominated pod.
	// Here we check for nil only for tests.
	if sched.SchedulingQueue != nil {
		sched.SchedulingQueue.AddNominatedPod(podInfo.PodInfo, nominatingInfo)
	}

	pod := podInfo.Pod
	msg := truncateMessage(err.Error())
	fwk.EventRecorder().Eventf(pod, nil, v1.EventTypeWarning, "FailedScheduling", "Scheduling", msg)
	if err := updatePod(sched.client, pod, &v1.PodCondition{
		Type:    v1.PodScheduled,
		Status:  v1.ConditionFalse,
		Reason:  reason,
		Message: err.Error(),
	}, nominatingInfo); err != nil {
		klog.ErrorS(err, "Error updating pod", "pod", klog.KObj(pod))
	}
}

// truncateMessage truncates a message if it hits the NoteLengthLimit.
func truncateMessage(message string) string {
	max := validation.NoteLengthLimit
	if len(message) <= max {
		return message
	}
	suffix := " ..."
	return message[:max-len(suffix)] + suffix
}

func updatePod(client clientset.Interface, pod *v1.Pod, condition *v1.PodCondition, nominatingInfo *framework.NominatingInfo) error {
	klog.V(3).InfoS("Updating pod condition", "pod", klog.KObj(pod), "conditionType", condition.Type, "conditionStatus", condition.Status, "conditionReason", condition.Reason)
	podStatusCopy := pod.Status.DeepCopy()
	// NominatedNodeName is updated only if we are trying to set it, and the value is
	// different from the existing one.
	nnnNeedsUpdate := nominatingInfo.Mode() == framework.ModeOverride && pod.Status.NominatedNodeName != nominatingInfo.NominatedNodeName
	if !podutil.UpdatePodCondition(podStatusCopy, condition) && !nnnNeedsUpdate {
		return nil
	}
	if nnnNeedsUpdate {
		podStatusCopy.NominatedNodeName = nominatingInfo.NominatedNodeName
	}
	return util.PatchPodStatus(client, pod, podStatusCopy)
}

// assume signals to the cache that a pod is already in the cache, so that binding can be asynchronous.
// assume modifies `assumed`.
func (sched *Scheduler) assume(assumed *v1.Pod, host string) error {
	// Optimistically assume that the binding will succeed and send it to apiserver
	// in the background.
	// If the binding fails, scheduler will release resources allocated to assumed pod
	// immediately.
	assumed.Spec.NodeName = host

	if err := sched.Cache.AssumePod(assumed); err != nil {
		klog.ErrorS(err, "Scheduler cache AssumePod failed")
		return err
	}
	// if "assumed" is a nominated pod, we should remove it from internal cache
	if sched.SchedulingQueue != nil {
		sched.SchedulingQueue.DeleteNominatedPodIfExists(assumed)
	}

	return nil
}

// bind binds a pod to a given node defined in a binding object.
// The precedence for binding is: (1) extenders and (2) framework plugins.
// We expect this to run asynchronously, so we handle binding metrics internally.
func (sched *Scheduler) bind(ctx context.Context, fwk framework.Framework, assumed *v1.Pod, targetNode string, state *framework.CycleState) (err error) {
	defer func() {
		sched.finishBinding(fwk, assumed, targetNode, err)
	}()

	bound, err := sched.extendersBinding(assumed, targetNode)
	if bound {
		return err
	}
	bindStatus := fwk.RunBindPlugins(ctx, state, assumed, targetNode)
	if bindStatus.IsSuccess() {
		return nil
	}
	if bindStatus.Code() == framework.Error {
		return bindStatus.AsError()
	}
	return fmt.Errorf("bind status: %s, %v", bindStatus.Code().String(), bindStatus.Message())
}

// TODO(#87159): Move this to a Plugin.
func (sched *Scheduler) extendersBinding(pod *v1.Pod, node string) (bool, error) {
	for _, extender := range sched.Extenders {
		if !extender.IsBinder() || !extender.IsInterested(pod) {
			continue
		}
		return true, extender.Bind(&v1.Binding{
			ObjectMeta: metav1.ObjectMeta{Namespace: pod.Namespace, Name: pod.Name, UID: pod.UID},
			Target:     v1.ObjectReference{Kind: "Node", Name: node},
		})
	}
	return false, nil
}

func (sched *Scheduler) finishBinding(fwk framework.Framework, assumed *v1.Pod, targetNode string, err error) {
	if finErr := sched.Cache.FinishBinding(assumed); finErr != nil {
		klog.ErrorS(finErr, "Scheduler cache FinishBinding failed")
	}
	if err != nil {
		klog.V(1).InfoS("Failed to bind pod", "pod", klog.KObj(assumed))
		return
	}

	fwk.EventRecorder().Eventf(assumed, nil, v1.EventTypeNormal, "Scheduled", "Binding", "Successfully assigned %v/%v to %v", assumed.Namespace, assumed.Name, targetNode)
}

var (
	clearNominatedNode = &framework.NominatingInfo{NominatingMode: framework.ModeOverride, NominatedNodeName: ""}
)

// 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
	fwk, err := sched.frameworkForPod(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.ErrorS(err, "Error occurred")
		return
	}
	if sched.skipPodSchedule(fwk, pod) {
		return
	}

	klog.V(3).InfoS("Attempting to schedule pod", "pod", klog.KObj(pod))

	// Synchronously attempt to find a fit for the pod.
	start := time.Now()
	state := framework.NewCycleState()
	state.SetRecordPluginMetrics(rand.Intn(100) < pluginMetricsSamplePercent)
	// Initialize an empty podsToActivate struct, which will be filled up by plugins or stay empty.
	podsToActivate := framework.NewPodsToActivate()
	state.Write(framework.PodsToActivateKey, podsToActivate)

	schedulingCycleCtx, cancel := context.WithCancel(ctx)
	defer cancel()
	scheduleResult, err := sched.SchedulePod(schedulingCycleCtx, fwk, state, pod)
	if err != nil {
		// SchedulePod() 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.
		var nominatingInfo *framework.NominatingInfo
		if fitError, ok := err.(*framework.FitError); ok {
			if !fwk.HasPostFilterPlugins() {
				klog.V(3).InfoS("No PostFilter plugins are registered, so no preemption will be performed")
			} else {
				// Run PostFilter plugins to try to make the pod schedulable in a future scheduling cycle.
				result, status := fwk.RunPostFilterPlugins(ctx, state, pod, fitError.Diagnosis.NodeToStatusMap)
				if status.Code() == framework.Error {
					klog.ErrorS(nil, "Status after running PostFilter plugins for pod", "pod", klog.KObj(pod), "status", status)
				} else {
					fitError.Diagnosis.PostFilterMsg = status.Message()
					klog.V(5).InfoS("Status after running PostFilter plugins for pod", "pod", klog.KObj(pod), "status", status)
				}
				if result != nil {
					nominatingInfo = result.NominatingInfo
				}
			}
			// 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.PodUnschedulable(fwk.ProfileName(), metrics.SinceInSeconds(start))
		} else if err == ErrNoNodesAvailable {
			nominatingInfo = clearNominatedNode
			// No nodes available is counted as unschedulable rather than an error.
			metrics.PodUnschedulable(fwk.ProfileName(), metrics.SinceInSeconds(start))
		} else {
			nominatingInfo = clearNominatedNode
			klog.ErrorS(err, "Error selecting node for pod", "pod", klog.KObj(pod))
			metrics.PodScheduleError(fwk.ProfileName(), metrics.SinceInSeconds(start))
		}
		sched.handleSchedulingFailure(fwk, podInfo, err, v1.PodReasonUnschedulable, nominatingInfo)
		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 modifies `assumedPod` by setting NodeName=scheduleResult.SuggestedHost
	err = sched.assume(assumedPod, scheduleResult.SuggestedHost)
	if err != nil {
		metrics.PodScheduleError(fwk.ProfileName(), metrics.SinceInSeconds(start))
		// 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.handleSchedulingFailure(fwk, assumedPodInfo, err, SchedulerError, clearNominatedNode)
		return
	}

	// Run the Reserve method of reserve plugins.
	if sts := fwk.RunReservePluginsReserve(schedulingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost); !sts.IsSuccess() {
		metrics.PodScheduleError(fwk.ProfileName(), metrics.SinceInSeconds(start))
		// trigger un-reserve to clean up state associated with the reserved Pod
		fwk.RunReservePluginsUnreserve(schedulingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)
		if forgetErr := sched.Cache.ForgetPod(assumedPod); forgetErr != nil {
			klog.ErrorS(forgetErr, "Scheduler cache ForgetPod failed")
		}
		sched.handleSchedulingFailure(fwk, assumedPodInfo, sts.AsError(), SchedulerError, clearNominatedNode)
		return
	}

	// Run "permit" plugins.
	runPermitStatus := fwk.RunPermitPlugins(schedulingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)
	if runPermitStatus.Code() != framework.Wait && !runPermitStatus.IsSuccess() {
		var reason string
		if runPermitStatus.IsUnschedulable() {
			metrics.PodUnschedulable(fwk.ProfileName(), metrics.SinceInSeconds(start))
			reason = v1.PodReasonUnschedulable
		} else {
			metrics.PodScheduleError(fwk.ProfileName(), metrics.SinceInSeconds(start))
			reason = SchedulerError
		}
		// One of the plugins returned status different than success or wait.
		fwk.RunReservePluginsUnreserve(schedulingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)
		if forgetErr := sched.Cache.ForgetPod(assumedPod); forgetErr != nil {
			klog.ErrorS(forgetErr, "Scheduler cache ForgetPod failed")
		}
		sched.handleSchedulingFailure(fwk, assumedPodInfo, runPermitStatus.AsError(), reason, clearNominatedNode)
		return
	}

	// At the end of a successful scheduling cycle, pop and move up Pods if needed.
	if len(podsToActivate.Map) != 0 {
		sched.SchedulingQueue.Activate(podsToActivate.Map)
		// Clear the entries after activation.
		podsToActivate.Map = make(map[string]*v1.Pod)
	}

	// 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(metrics.Binding).Inc()
		defer metrics.SchedulerGoroutines.WithLabelValues(metrics.Binding).Dec()

		waitOnPermitStatus := fwk.WaitOnPermit(bindingCycleCtx, assumedPod)
		if !waitOnPermitStatus.IsSuccess() {
			var reason string
			if waitOnPermitStatus.IsUnschedulable() {
				metrics.PodUnschedulable(fwk.ProfileName(), metrics.SinceInSeconds(start))
				reason = v1.PodReasonUnschedulable
			} else {
				metrics.PodScheduleError(fwk.ProfileName(), metrics.SinceInSeconds(start))
				reason = SchedulerError
			}
			// trigger un-reserve plugins to clean up state associated with the reserved Pod
			fwk.RunReservePluginsUnreserve(bindingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)
			if forgetErr := sched.Cache.ForgetPod(assumedPod); forgetErr != nil {
				klog.ErrorS(forgetErr, "scheduler cache ForgetPod failed")
			} else {
				// "Forget"ing an assumed Pod in binding cycle should be treated as a PodDelete event,
				// as the assumed Pod had occupied a certain amount of resources in scheduler cache.
				// TODO(#103853): de-duplicate the logic.
				// Avoid moving the assumed Pod itself as it's always Unschedulable.
				// It's intentional to "defer" this operation; otherwise MoveAllToActiveOrBackoffQueue() would
				// update `q.moveRequest` and thus move the assumed pod to backoffQ anyways.
				defer sched.SchedulingQueue.MoveAllToActiveOrBackoffQueue(internalqueue.AssignedPodDelete, func(pod *v1.Pod) bool {
					return assumedPod.UID != pod.UID
				})
			}
			sched.handleSchedulingFailure(fwk, assumedPodInfo, waitOnPermitStatus.AsError(), reason, clearNominatedNode)
			return
		}

		// Run "prebind" plugins.
		preBindStatus := fwk.RunPreBindPlugins(bindingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)
		if !preBindStatus.IsSuccess() {
			metrics.PodScheduleError(fwk.ProfileName(), metrics.SinceInSeconds(start))
			// trigger un-reserve plugins to clean up state associated with the reserved Pod
			fwk.RunReservePluginsUnreserve(bindingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)
			if forgetErr := sched.Cache.ForgetPod(assumedPod); forgetErr != nil {
				klog.ErrorS(forgetErr, "scheduler cache ForgetPod failed")
			} else {
				// "Forget"ing an assumed Pod in binding cycle should be treated as a PodDelete event,
				// as the assumed Pod had occupied a certain amount of resources in scheduler cache.
				// TODO(#103853): de-duplicate the logic.
				sched.SchedulingQueue.MoveAllToActiveOrBackoffQueue(internalqueue.AssignedPodDelete, nil)
			}
			sched.handleSchedulingFailure(fwk, assumedPodInfo, preBindStatus.AsError(), SchedulerError, clearNominatedNode)
			return
		}

		err := sched.bind(bindingCycleCtx, fwk, assumedPod, scheduleResult.SuggestedHost, state)
		if err != nil {
			metrics.PodScheduleError(fwk.ProfileName(), metrics.SinceInSeconds(start))
			// trigger un-reserve plugins to clean up state associated with the reserved Pod
			fwk.RunReservePluginsUnreserve(bindingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)
			if err := sched.Cache.ForgetPod(assumedPod); err != nil {
				klog.ErrorS(err, "scheduler cache ForgetPod failed")
			} else {
				// "Forget"ing an assumed Pod in binding cycle should be treated as a PodDelete event,
				// as the assumed Pod had occupied a certain amount of resources in scheduler cache.
				// TODO(#103853): de-duplicate the logic.
				sched.SchedulingQueue.MoveAllToActiveOrBackoffQueue(internalqueue.AssignedPodDelete, nil)
			}
			sched.handleSchedulingFailure(fwk, assumedPodInfo, fmt.Errorf("binding rejected: %w", err), SchedulerError, clearNominatedNode)
		} else {
			// Calculating nodeResourceString can be heavy. Avoid it if klog verbosity is below 2.
			klog.V(2).InfoS("Successfully bound pod to node", "pod", klog.KObj(pod), "node", scheduleResult.SuggestedHost, "evaluatedNodes", scheduleResult.EvaluatedNodes, "feasibleNodes", scheduleResult.FeasibleNodes)
			metrics.PodScheduled(fwk.ProfileName(), metrics.SinceInSeconds(start))
			metrics.PodSchedulingAttempts.Observe(float64(podInfo.Attempts))
			metrics.PodSchedulingDuration.WithLabelValues(getAttemptsLabel(podInfo)).Observe(metrics.SinceInSeconds(podInfo.InitialAttemptTimestamp))

			// Run "postbind" plugins.
			fwk.RunPostBindPlugins(bindingCycleCtx, state, assumedPod, scheduleResult.SuggestedHost)

			// At the end of a successful binding cycle, move up Pods if needed.
			if len(podsToActivate.Map) != 0 {
				sched.SchedulingQueue.Activate(podsToActivate.Map)
				// Unlike the logic in scheduling cycle, we don't bother deleting the entries
				// as `podsToActivate.Map` is no longer consumed.
			}
		}
	}()
}

func getAttemptsLabel(p *framework.QueuedPodInfo) string {
	// We breakdown the pod scheduling duration by attempts capped to a limit
	// to avoid ending up with a high cardinality metric.
	if p.Attempts >= 15 {
		return "15+"
	}
	return strconv.Itoa(p.Attempts)
}

func (sched *Scheduler) frameworkForPod(pod *v1.Pod) (framework.Framework, error) {
	fwk, ok := sched.Profiles[pod.Spec.SchedulerName]
	if !ok {
		return nil, fmt.Errorf("profile not found for scheduler name %q", pod.Spec.SchedulerName)
	}
	return fwk, nil
}

// skipPodSchedule returns true if we could skip scheduling the pod for specified cases.
func (sched *Scheduler) skipPodSchedule(fwk framework.Framework, pod *v1.Pod) bool {
	// Case 1: pod is being deleted.
	if pod.DeletionTimestamp != nil {
		fwk.EventRecorder().Eventf(pod, nil, v1.EventTypeWarning, "FailedScheduling", "Scheduling", "skip schedule deleting pod: %v/%v", pod.Namespace, pod.Name)
		klog.V(3).InfoS("Skip schedule deleting pod", "pod", klog.KObj(pod))
		return true
	}

	// Case 2: pod that has been assumed could be skipped.
	// An assumed pod can be added again to the scheduling queue if it got an update event
	// during its previous scheduling cycle but before getting assumed.
	isAssumed, err := sched.Cache.IsAssumedPod(pod)
	if err != nil {
		utilruntime.HandleError(fmt.Errorf("failed to check whether pod %s/%s is assumed: %v", pod.Namespace, pod.Name, err))
		return false
	}
	return isAssumed
}

// NewInformerFactory creates a SharedInformerFactory and initializes a scheduler specific
// in-place podInformer.
func NewInformerFactory(cs clientset.Interface, resyncPeriod time.Duration) informers.SharedInformerFactory {
	informerFactory := informers.NewSharedInformerFactory(cs, resyncPeriod)
	informerFactory.InformerFor(&v1.Pod{}, newPodInformer)
	return informerFactory
}

// newPodInformer creates a shared index informer that returns only non-terminal pods.
func newPodInformer(cs clientset.Interface, resyncPeriod time.Duration) cache.SharedIndexInformer {
	selector := fmt.Sprintf("status.phase!=%v,status.phase!=%v", v1.PodSucceeded, v1.PodFailed)
	tweakListOptions := func(options *metav1.ListOptions) {
		options.FieldSelector = selector
	}
	return coreinformers.NewFilteredPodInformer(cs, metav1.NamespaceAll, resyncPeriod, nil, tweakListOptions)
}

// snapshot snapshots scheduler cache and node infos for all fit and priority
// functions.
func (sched *Scheduler) snapshot() error {
	// Used for all fit and priority funcs.
	return sched.Cache.UpdateSnapshot(sched.nodeInfoSnapshot)
}

// schedulePod tries to schedule the given pod to one of the nodes in the node list.
// If it succeeds, it will return the name of the node.
// If it fails, it will return a FitError with reasons.
func (sched *Scheduler) schedulePod(ctx context.Context, fwk framework.Framework, state *framework.CycleState, pod *v1.Pod) (result ScheduleResult, err error) {
	trace := utiltrace.New("Scheduling", utiltrace.Field{Key: "namespace", Value: pod.Namespace}, utiltrace.Field{Key: "name", Value: pod.Name})
	defer trace.LogIfLong(100 * time.Millisecond)

	if err := sched.snapshot(); err != nil {
		return result, err
	}
	trace.Step("Snapshotting scheduler cache and node infos done")

	if sched.nodeInfoSnapshot.NumNodes() == 0 {
		return result, ErrNoNodesAvailable
	}

	feasibleNodes, diagnosis, err := sched.findNodesThatFitPod(ctx, fwk, state, pod)
	if err != nil {
		return result, err
	}
	trace.Step("Computing predicates done")

	if len(feasibleNodes) == 0 {
		return result, &framework.FitError{
			Pod:         pod,
			NumAllNodes: sched.nodeInfoSnapshot.NumNodes(),
			Diagnosis:   diagnosis,
		}
	}

	// When only one node after predicate, just use it.
	if len(feasibleNodes) == 1 {
		return ScheduleResult{
			SuggestedHost:  feasibleNodes[0].Name,
			EvaluatedNodes: 1 + len(diagnosis.NodeToStatusMap),
			FeasibleNodes:  1,
		}, nil
	}

	priorityList, err := prioritizeNodes(ctx, sched.Extenders, fwk, state, pod, feasibleNodes)
	if err != nil {
		return result, err
	}

	host, err := selectHost(priorityList)
	trace.Step("Prioritizing done")

	return ScheduleResult{
		SuggestedHost:  host,
		EvaluatedNodes: len(feasibleNodes) + len(diagnosis.NodeToStatusMap),
		FeasibleNodes:  len(feasibleNodes),
	}, err
}

// selectHost takes a prioritized list of nodes and then picks one
// in a reservoir sampling manner from the nodes that had the highest score.
func selectHost(nodeScoreList framework.NodeScoreList) (string, error) {
	if len(nodeScoreList) == 0 {
		return "", fmt.Errorf("empty priorityList")
	}
	maxScore := nodeScoreList[0].Score
	selected := nodeScoreList[0].Name
	cntOfMaxScore := 1
	for _, ns := range nodeScoreList[1:] {
		if ns.Score > maxScore {
			maxScore = ns.Score
			selected = ns.Name
			cntOfMaxScore = 1
		} else if ns.Score == maxScore {
			cntOfMaxScore++
			if rand.Intn(cntOfMaxScore) == 0 {
				// Replace the candidate with probability of 1/cntOfMaxScore
				selected = ns.Name
			}
		}
	}
	return selected, nil
}

// numFeasibleNodesToFind returns the number of feasible nodes that once found, the scheduler stops
// its search for more feasible nodes.
func (sched *Scheduler) numFeasibleNodesToFind(numAllNodes int32) (numNodes int32) {
	if numAllNodes < minFeasibleNodesToFind || sched.percentageOfNodesToScore >= 100 {
		return numAllNodes
	}

	adaptivePercentage := sched.percentageOfNodesToScore
	if adaptivePercentage <= 0 {
		basePercentageOfNodesToScore := int32(50)
		adaptivePercentage = basePercentageOfNodesToScore - numAllNodes/125
		if adaptivePercentage < minFeasibleNodesPercentageToFind {
			adaptivePercentage = minFeasibleNodesPercentageToFind
		}
	}

	numNodes = numAllNodes * adaptivePercentage / 100
	if numNodes < minFeasibleNodesToFind {
		return minFeasibleNodesToFind
	}

	return numNodes
}

func (sched *Scheduler) evaluateNominatedNode(ctx context.Context, pod *v1.Pod, fwk framework.Framework, state *framework.CycleState, diagnosis framework.Diagnosis) ([]*v1.Node, error) {
	nnn := pod.Status.NominatedNodeName
	nodeInfo, err := sched.nodeInfoSnapshot.Get(nnn)
	if err != nil {
		return nil, err
	}
	node := []*framework.NodeInfo{nodeInfo}
	feasibleNodes, err := sched.findNodesThatPassFilters(ctx, fwk, state, pod, diagnosis, node)
	if err != nil {
		return nil, err
	}

	feasibleNodes, err = findNodesThatPassExtenders(sched.Extenders, pod, feasibleNodes, diagnosis.NodeToStatusMap)
	if err != nil {
		return nil, err
	}

	return feasibleNodes, nil
}

// Filters the nodes to find the ones that fit the pod based on the framework
// filter plugins and filter extenders.
func (sched *Scheduler) findNodesThatFitPod(ctx context.Context, fwk framework.Framework, state *framework.CycleState, pod *v1.Pod) ([]*v1.Node, framework.Diagnosis, error) {
	diagnosis := framework.Diagnosis{
		NodeToStatusMap:      make(framework.NodeToStatusMap),
		UnschedulablePlugins: sets.NewString(),
	}

	// Run "prefilter" plugins.
	s := fwk.RunPreFilterPlugins(ctx, state, pod)
	allNodes, err := sched.nodeInfoSnapshot.NodeInfos().List()
	if err != nil {
		return nil, diagnosis, err
	}
	if !s.IsSuccess() {
		if !s.IsUnschedulable() {
			return nil, diagnosis, s.AsError()
		}
		// All nodes will have the same status. Some non trivial refactoring is
		// needed to avoid this copy.
		for _, n := range allNodes {
			diagnosis.NodeToStatusMap[n.Node().Name] = s
		}
		// Status satisfying IsUnschedulable() gets injected into diagnosis.UnschedulablePlugins.
		diagnosis.UnschedulablePlugins.Insert(s.FailedPlugin())
		return nil, diagnosis, nil
	}

	// "NominatedNodeName" can potentially be set in a previous scheduling cycle as a result of preemption.
	// This node is likely the only candidate that will fit the pod, and hence we try it first before iterating over all nodes.
	if len(pod.Status.NominatedNodeName) > 0 {
		feasibleNodes, err := sched.evaluateNominatedNode(ctx, pod, fwk, state, diagnosis)
		if err != nil {
			klog.ErrorS(err, "Evaluation failed on nominated node", "pod", klog.KObj(pod), "node", pod.Status.NominatedNodeName)
		}
		// Nominated node passes all the filters, scheduler is good to assign this node to the pod.
		if len(feasibleNodes) != 0 {
			return feasibleNodes, diagnosis, nil
		}
	}
	feasibleNodes, err := sched.findNodesThatPassFilters(ctx, fwk, state, pod, diagnosis, allNodes)
	if err != nil {
		return nil, diagnosis, err
	}

	feasibleNodes, err = findNodesThatPassExtenders(sched.Extenders, pod, feasibleNodes, diagnosis.NodeToStatusMap)
	if err != nil {
		return nil, diagnosis, err
	}
	return feasibleNodes, diagnosis, nil
}

// findNodesThatPassFilters finds the nodes that fit the filter plugins.
func (sched *Scheduler) findNodesThatPassFilters(
	ctx context.Context,
	fwk framework.Framework,
	state *framework.CycleState,
	pod *v1.Pod,
	diagnosis framework.Diagnosis,
	nodes []*framework.NodeInfo) ([]*v1.Node, error) {
	numNodesToFind := sched.numFeasibleNodesToFind(int32(len(nodes)))

	// Create feasible list with enough space to avoid growing it
	// and allow assigning.
	feasibleNodes := make([]*v1.Node, numNodesToFind)

	if !fwk.HasFilterPlugins() {
		length := len(nodes)
		for i := range feasibleNodes {
			feasibleNodes[i] = nodes[(sched.nextStartNodeIndex+i)%length].Node()
		}
		sched.nextStartNodeIndex = (sched.nextStartNodeIndex + len(feasibleNodes)) % length
		return feasibleNodes, nil
	}

	errCh := parallelize.NewErrorChannel()
	var statusesLock sync.Mutex
	var feasibleNodesLen int32
	ctx, cancel := context.WithCancel(ctx)
	checkNode := func(i int) {
		// We check the nodes starting from where we left off in the previous scheduling cycle,
		// this is to make sure all nodes have the same chance of being examined across pods.
		nodeInfo := nodes[(sched.nextStartNodeIndex+i)%len(nodes)]
		status := fwk.RunFilterPluginsWithNominatedPods(ctx, state, pod, nodeInfo)
		if status.Code() == framework.Error {
			errCh.SendErrorWithCancel(status.AsError(), cancel)
			return
		}
		if status.IsSuccess() {
			length := atomic.AddInt32(&feasibleNodesLen, 1)
			if length > numNodesToFind {
				cancel()
				atomic.AddInt32(&feasibleNodesLen, -1)
			} else {
				feasibleNodes[length-1] = nodeInfo.Node()
			}
		} else {
			statusesLock.Lock()
			diagnosis.NodeToStatusMap[nodeInfo.Node().Name] = status
			diagnosis.UnschedulablePlugins.Insert(status.FailedPlugin())
			statusesLock.Unlock()
		}
	}

	beginCheckNode := time.Now()
	statusCode := framework.Success
	defer func() {
		// We record Filter extension point latency here instead of in framework.go because framework.RunFilterPlugins
		// function is called for each node, whereas we want to have an overall latency for all nodes per scheduling cycle.
		// Note that this latency also includes latency for `addNominatedPods`, which calls framework.RunPreFilterAddPod.
		metrics.FrameworkExtensionPointDuration.WithLabelValues(frameworkruntime.Filter, statusCode.String(), fwk.ProfileName()).Observe(metrics.SinceInSeconds(beginCheckNode))
	}()

	// Stops searching for more nodes once the configured number of feasible nodes
	// are found.
	fwk.Parallelizer().Until(ctx, len(nodes), checkNode)
	processedNodes := int(feasibleNodesLen) + len(diagnosis.NodeToStatusMap)
	sched.nextStartNodeIndex = (sched.nextStartNodeIndex + processedNodes) % len(nodes)

	feasibleNodes = feasibleNodes[:feasibleNodesLen]
	if err := errCh.ReceiveError(); err != nil {
		statusCode = framework.Error
		return nil, err
	}
	return feasibleNodes, nil
}

func findNodesThatPassExtenders(extenders []framework.Extender, pod *v1.Pod, feasibleNodes []*v1.Node, statuses framework.NodeToStatusMap) ([]*v1.Node, error) {
	// Extenders are called sequentially.
	// Nodes in original feasibleNodes can be excluded in one extender, and pass on to the next
	// extender in a decreasing manner.
	for _, extender := range extenders {
		if len(feasibleNodes) == 0 {
			break
		}
		if !extender.IsInterested(pod) {
			continue
		}

		// Status of failed nodes in failedAndUnresolvableMap will be added or overwritten in <statuses>,
		// so that the scheduler framework can respect the UnschedulableAndUnresolvable status for
		// particular nodes, and this may eventually improve preemption efficiency.
		// Note: users are recommended to configure the extenders that may return UnschedulableAndUnresolvable
		// status ahead of others.
		feasibleList, failedMap, failedAndUnresolvableMap, err := extender.Filter(pod, feasibleNodes)
		if err != nil {
			if extender.IsIgnorable() {
				klog.InfoS("Skipping extender as it returned error and has ignorable flag set", "extender", extender, "err", err)
				continue
			}
			return nil, err
		}

		for failedNodeName, failedMsg := range failedAndUnresolvableMap {
			var aggregatedReasons []string
			if _, found := statuses[failedNodeName]; found {
				aggregatedReasons = statuses[failedNodeName].Reasons()
			}
			aggregatedReasons = append(aggregatedReasons, failedMsg)
			statuses[failedNodeName] = framework.NewStatus(framework.UnschedulableAndUnresolvable, aggregatedReasons...)
		}

		for failedNodeName, failedMsg := range failedMap {
			if _, found := failedAndUnresolvableMap[failedNodeName]; found {
				// failedAndUnresolvableMap takes precedence over failedMap
				// note that this only happens if the extender returns the node in both maps
				continue
			}
			if _, found := statuses[failedNodeName]; !found {
				statuses[failedNodeName] = framework.NewStatus(framework.Unschedulable, failedMsg)
			} else {
				statuses[failedNodeName].AppendReason(failedMsg)
			}
		}

		feasibleNodes = feasibleList
	}
	return feasibleNodes, nil
}

// prioritizeNodes prioritizes the nodes by running the score plugins,
// which return a score for each node from the call to RunScorePlugins().
// The scores from each plugin are added together to make the score for that node, then
// any extenders are run as well.
// All scores are finally combined (added) to get the total weighted scores of all nodes
func prioritizeNodes(
	ctx context.Context,
	extenders []framework.Extender,
	fwk framework.Framework,
	state *framework.CycleState,
	pod *v1.Pod,
	nodes []*v1.Node,
) (framework.NodeScoreList, error) {
	// If no priority configs are provided, then all nodes will have a score of one.
	// This is required to generate the priority list in the required format
	if len(extenders) == 0 && !fwk.HasScorePlugins() {
		result := make(framework.NodeScoreList, 0, len(nodes))
		for i := range nodes {
			result = append(result, framework.NodeScore{
				Name:  nodes[i].Name,
				Score: 1,
			})
		}
		return result, nil
	}

	// Run PreScore plugins.
	preScoreStatus := fwk.RunPreScorePlugins(ctx, state, pod, nodes)
	if !preScoreStatus.IsSuccess() {
		return nil, preScoreStatus.AsError()
	}

	// Run the Score plugins.
	scoresMap, scoreStatus := fwk.RunScorePlugins(ctx, state, pod, nodes)
	if !scoreStatus.IsSuccess() {
		return nil, scoreStatus.AsError()
	}

	// Additional details logged at level 10 if enabled.
	klogV := klog.V(10)
	if klogV.Enabled() {
		for plugin, nodeScoreList := range scoresMap {
			for _, nodeScore := range nodeScoreList {
				klogV.InfoS("Plugin scored node for pod", "pod", klog.KObj(pod), "plugin", plugin, "node", nodeScore.Name, "score", nodeScore.Score)
			}
		}
	}

	// Summarize all scores.
	result := make(framework.NodeScoreList, 0, len(nodes))

	for i := range nodes {
		result = append(result, framework.NodeScore{Name: nodes[i].Name, Score: 0})
		for j := range scoresMap {
			result[i].Score += scoresMap[j][i].Score
		}
	}

	if len(extenders) != 0 && nodes != nil {
		var mu sync.Mutex
		var wg sync.WaitGroup
		combinedScores := make(map[string]int64, len(nodes))
		for i := range extenders {
			if !extenders[i].IsInterested(pod) {
				continue
			}
			wg.Add(1)
			go func(extIndex int) {
				metrics.SchedulerGoroutines.WithLabelValues(metrics.PrioritizingExtender).Inc()
				defer func() {
					metrics.SchedulerGoroutines.WithLabelValues(metrics.PrioritizingExtender).Dec()
					wg.Done()
				}()
				prioritizedList, weight, err := extenders[extIndex].Prioritize(pod, nodes)
				if err != nil {
					// Prioritization errors from extender can be ignored, let k8s/other extenders determine the priorities
					klog.V(5).InfoS("Failed to run extender's priority function. No score given by this extender.", "error", err, "pod", klog.KObj(pod), "extender", extenders[extIndex].Name())
					return
				}
				mu.Lock()
				for i := range *prioritizedList {
					host, score := (*prioritizedList)[i].Host, (*prioritizedList)[i].Score
					if klogV.Enabled() {
						klogV.InfoS("Extender scored node for pod", "pod", klog.KObj(pod), "extender", extenders[extIndex].Name(), "node", host, "score", score)
					}
					combinedScores[host] += score * weight
				}
				mu.Unlock()
			}(i)
		}
		// wait for all go routines to finish
		wg.Wait()
		for i := range result {
			// MaxExtenderPriority may diverge from the max priority used in the scheduler and defined by MaxNodeScore,
			// therefore we need to scale the score returned by extenders to the score range used by the scheduler.
			result[i].Score += combinedScores[result[i].Name] * (framework.MaxNodeScore / extenderv1.MaxExtenderPriority)
		}
	}

	if klogV.Enabled() {
		for i := range result {
			klogV.InfoS("Calculated node's final score for pod", "pod", klog.KObj(pod), "node", result[i].Name, "score", result[i].Score)
		}
	}
	return result, nil
}