原 荐 深入分析Kubernetes Sch

func (sched *Scheduler) preempt(preemptor *v1.Pod, scheduleErr error) (string, error) {
	...
	node, victims, nominatedPodsToClear, err := sched.config.Algorithm.Preempt(preemptor, sched.config.NodeLister, scheduleErr)
	...
	var nodeName = ""
	if node != nil {
		nodeName = node.Name
		err = sched.config.PodPreemptor.SetNominatedNodeName(preemptor, nodeName)
		if err != nil {
			glog.Errorf("Error in preemption process. Cannot update pod %v annotations: %v", preemptor.Name, err)
			return "", err
		}
		...
	}
	// Clearing nominated pods should happen outside of "if node != nil". Node could
	// be nil when a pod with nominated node name is eligible to preempt again,
	// but preemption logic does not find any node for it. In that case Preempt()
	// function of generic_scheduler.go returns the pod itself for removal of the annotation.
	for _, p := range nominatedPodsToClear {
		rErr := sched.config.PodPreemptor.RemoveNominatedNodeName(p)
		if rErr != nil {
			glog.Errorf("Cannot remove nominated node annotation of pod: %v", rErr)
			// We do not return as this error is not critical.
		}
	}
	return nodeName, err
}

- node：抢占发生的最佳node；
- victims：待删除的pods，以释放资源给preemptor；
- nominatedPodsToClear：那些将要被删除`.Status.NominatedNodeName`的Pods列表，这些Pods是首先是属于PriorityQueue中的nominatedPods Cache中的Pods，并且他们的Pod Priority要低于preemptor Pod Priority，意味着这些nominatedPods已经不再适合调度到之前抢占时选择的这个node上了。

func podFitsOnNode(
	pod *v1.Pod,
	meta algorithm.PredicateMetadata,
	info *schedulercache.NodeInfo,
	predicateFuncs map[string]algorithm.FitPredicate,
	ecache *EquivalenceCache,
	queue SchedulingQueue,
	alwaysCheckAllPredicates bool,
	equivCacheInfo *equivalenceClassInfo,
) (bool, []algorithm.PredicateFailureReason, error) {
	var (
		eCacheAvailable  bool
		failedPredicates []algorithm.PredicateFailureReason
	)
	predicateResults := make(map[string]HostPredicate)

	podsAdded := false
	
	for i := 0; i < 2; i++ {
		metaToUse := meta
		nodeInfoToUse := info
		if i == 0 {
			podsAdded, metaToUse, nodeInfoToUse = addNominatedPods(util.GetPodPriority(pod), meta, info, queue)
		} else if !podsAdded || len(failedPredicates) != 0 {  // 有问题吧？应该是podsAdded，而不是!podsAdded
			break
		}
		// Bypass eCache if node has any nominated pods.
		// TODO(bsalamat): consider using eCache and adding proper eCache invalidations
		// when pods are nominated or their nominations change.
		eCacheAvailable = equivCacheInfo != nil && !podsAdded
		for _, predicateKey := range predicates.Ordering() {
			var (
				fit     bool
				reasons []algorithm.PredicateFailureReason
				err     error
			)
			
				func() {
					var invalid bool
					if eCacheAvailable {
						...
					}

					if !eCacheAvailable || invalid {
						// we need to execute predicate functions since equivalence cache does not work
						fit, reasons, err = predicate(pod, metaToUse, nodeInfoToUse)
						if err != nil {
							return
						}

						...
					}
				}()

				...
			}
		}
	}

	return len(failedPredicates) == 0, failedPredicates, nil
}

// addNominatedPods adds pods with equal or greater priority which are nominated
// to run on the node given in nodeInfo to meta and nodeInfo. It returns 1) whether
// any pod was found, 2) augmented meta data, 3) augmented nodeInfo.
func addNominatedPods(podPriority int32, meta algorithm.PredicateMetadata,
	nodeInfo *schedulercache.NodeInfo, queue SchedulingQueue) (bool, algorithm.PredicateMetadata,
	*schedulercache.NodeInfo) {
	if queue == nil || nodeInfo == nil || nodeInfo.Node() == nil {
		// This may happen only in tests.
		return false, meta, nodeInfo
	}
	nominatedPods := queue.WaitingPodsForNode(nodeInfo.Node().Name)
	if nominatedPods == nil || len(nominatedPods) == 0 {
		return false, meta, nodeInfo
	}
	var metaOut algorithm.PredicateMetadata
	if meta != nil {
		metaOut = meta.ShallowCopy()
	}
	nodeInfoOut := nodeInfo.Clone()
	for _, p := range nominatedPods {
		if util.GetPodPriority(p) >= podPriority {
			nodeInfoOut.AddPod(p)
			if metaOut != nil {
				metaOut.AddPod(p, nodeInfoOut)
			}
		}
	}
	return true, metaOut, nodeInfoOut
}

// WaitingPodsForNode returns pods that are nominated to run on the given node,
// but they are waiting for other pods to be removed from the node before they
// can be actually scheduled.
func (p *PriorityQueue) WaitingPodsForNode(nodeName string) []*v1.Pod {
	p.lock.RLock()
	defer p.lock.RUnlock()
	if list, ok := p.nominatedPods[nodeName]; ok {
		return list
	}
	return nil
}

// Add adds a pod to the active queue. It should be called only when a new pod
// is added so there is no chance the pod is already in either queue.
func (p *PriorityQueue) Add(pod *v1.Pod) error {
	p.lock.Lock()
	defer p.lock.Unlock()
	err := p.activeQ.Add(pod)
	if err != nil {
		glog.Errorf("Error adding pod %v to the scheduling queue: %v", pod.Name, err)
	} else {
		if p.unschedulableQ.get(pod) != nil {
			glog.Errorf("Error: pod %v is already in the unschedulable queue.", pod.Name)
			p.deleteNominatedPodIfExists(pod)
			p.unschedulableQ.delete(pod)
		}
		p.addNominatedPodIfNeeded(pod)
		p.cond.Broadcast()
	}
	return err
}

func (p *PriorityQueue) addNominatedPodIfNeeded(pod *v1.Pod) {
	nnn := NominatedNodeName(pod)
	if len(nnn) > 0 {
		for _, np := range p.nominatedPods[nnn] {
			if np.UID == pod.UID {
				glog.Errorf("Pod %v/%v already exists in the nominated map!", pod.Namespace, pod.Name)
				return
			}
		}
		p.nominatedPods[nnn] = append(p.nominatedPods[nnn], pod)
	}
}

func (p *PriorityQueue) AddUnschedulableIfNotPresent(pod *v1.Pod) error {
	p.lock.Lock()
	defer p.lock.Unlock()
	if p.unschedulableQ.get(pod) != nil {
		return fmt.Errorf("pod is already present in unschedulableQ")
	}
	if _, exists, _ := p.activeQ.Get(pod); exists {
		return fmt.Errorf("pod is already present in the activeQ")
	}
	if !p.receivedMoveRequest && isPodUnschedulable(pod) {
		p.unschedulableQ.addOrUpdate(pod)
		p.addNominatedPodIfNeeded(pod)
		return nil
	}
	err := p.activeQ.Add(pod)
	if err == nil {
		p.addNominatedPodIfNeeded(pod)
		p.cond.Broadcast()
	}
	return err
}

// Update updates a pod in the active queue if present. Otherwise, it removes
// the item from the unschedulable queue and adds the updated one to the active
// queue.
func (p *PriorityQueue) Update(oldPod, newPod *v1.Pod) error {
	p.lock.Lock()
	defer p.lock.Unlock()
	// If the pod is already in the active queue, just update it there.
	if _, exists, _ := p.activeQ.Get(newPod); exists {
		p.updateNominatedPod(oldPod, newPod)
		err := p.activeQ.Update(newPod)
		return err
	}
	// If the pod is in the unschedulable queue, updating it may make it schedulable.
	if usPod := p.unschedulableQ.get(newPod); usPod != nil {
		p.updateNominatedPod(oldPod, newPod)
		if isPodUpdated(oldPod, newPod) {
			p.unschedulableQ.delete(usPod)
			err := p.activeQ.Add(newPod)
			if err == nil {
				p.cond.Broadcast()
			}
			return err
		}
		p.unschedulableQ.addOrUpdate(newPod)
		return nil
	}
	// If pod is not in any of the two queue, we put it in the active queue.
	err := p.activeQ.Add(newPod)
	if err == nil {
		p.addNominatedPodIfNeeded(newPod)
		p.cond.Broadcast()
	}
	return err
}

// updateNominatedPod updates a pod in the nominatedPods.
func (p *PriorityQueue) updateNominatedPod(oldPod, newPod *v1.Pod) {
	// Even if the nominated node name of the Pod is not changed, we must delete and add it again
	// to ensure that its pointer is updated.
	p.deleteNominatedPodIfExists(oldPod)
	p.addNominatedPodIfNeeded(newPod)
}

// Delete deletes the item from either of the two queues. It assumes the pod is
// only in one queue.
func (p *PriorityQueue) Delete(pod *v1.Pod) error {
	p.lock.Lock()
	defer p.lock.Unlock()
	p.deleteNominatedPodIfExists(pod)
	err := p.activeQ.Delete(pod)
	if err != nil { // The item was probably not found in the activeQ.
		p.unschedulableQ.delete(pod)
	}
	return nil
}

func (p *PriorityQueue) deleteNominatedPodIfExists(pod *v1.Pod) {
	nnn := NominatedNodeName(pod)
	if len(nnn) > 0 {
		for i, np := range p.nominatedPods[nnn] {
			if np.UID == pod.UID {
				p.nominatedPods[nnn] = append(p.nominatedPods[nnn][:i], p.nominatedPods[nnn][i+1:]...)
				if len(p.nominatedPods[nnn]) == 0 {
					delete(p.nominatedPods, nnn)
				}
				break
			}
		}
	}
}