kube-scheduler 调度中的流氓兔 - preempt

preempt 作用

这兔子在pod调度失败后，在没有禁用抢占调度的情况下，开始了“流氓式”的调度。
它的作用是抢占低优先级的pod，如果成功了，那么就更新pod spec，返回nodename。

func (sched *Scheduler) preempt(ctx context.Context, prof *profile.Profile, state *framework.CycleState, preemptor *v1.Pod, scheduleErr error) (string, error) {
	preemptor, err := sched.podPreemptor.getUpdatedPod(preemptor)
	if err != nil {
		klog.Errorf("Error getting the updated preemptor pod object: %v", err)
		return "", err
	}

	node, victims, nominatedPodsToClear, err := sched.Algorithm.Preempt(ctx, prof, state, preemptor, scheduleErr)
	if err != nil {
		klog.Errorf("Error preempting victims to make room for %v/%v: %v", preemptor.Namespace, preemptor.Name, err)
		return "", err
	}
	var nodeName = ""
	if node != nil {
		nodeName = node.Name
		// 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.
		sched.SchedulingQueue.UpdateNominatedPodForNode(preemptor, nodeName)

		// Make a call to update nominated node name of the pod on the API server.
		err = sched.podPreemptor.setNominatedNodeName(preemptor, nodeName)
		if err != nil {
			klog.Errorf("Error in preemption process. Cannot set 'NominatedPod' on pod %v/%v: %v", preemptor.Namespace, preemptor.Name, err)
			sched.SchedulingQueue.DeleteNominatedPodIfExists(preemptor)
			return "", err
		}

		for _, victim := range victims {
			if err := sched.podPreemptor.deletePod(victim); err != nil {
				klog.Errorf("Error preempting pod %v/%v: %v", victim.Namespace, victim.Name, err)
				return "", err
			}
			// If the victim is a WaitingPod, send a reject message to the PermitPlugin
			if waitingPod := prof.GetWaitingPod(victim.UID); waitingPod != nil {
				waitingPod.Reject("preempted")
			}
			prof.Recorder.Eventf(victim, preemptor, v1.EventTypeNormal, "Preempted", "Preempting", "Preempted by %v/%v on node %v", preemptor.Namespace, preemptor.Name, nodeName)

		}
		metrics.PreemptionVictims.Observe(float64(len(victims)))
	}
	// 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 'NominatedPod' field.
	for _, p := range nominatedPodsToClear {
		rErr := sched.podPreemptor.removeNominatedNodeName(p)
		if rErr != nil {
			klog.Errorf("Cannot remove 'NominatedPod' field of pod: %v", rErr)
			// We do not return as this error is not critical.
		}
	}
	return nodeName, err
}

执行sched.Algorithm.Preempt方法，它的执行逻辑是：

1. 如果抢占成功
2. 更新scheudling queue中的pod信息，要不然他就会无休止的调度下去
3. 通知API server设置这个抢占成功pod的node name（更新）
4. 遍历victims，也就是被抢占的pod，把这些pod删除，如果发现这个pod本身处于等待中，直接发生拒绝。
5. 最后把这些提名的pod移除，防止再次被抢占。

func (g *genericScheduler) Preempt(ctx context.Context, prof *profile.Profile, state *framework.CycleState, pod *v1.Pod, scheduleErr error) (*v1.Node, []*v1.Pod, []*v1.Pod, error) {
	// Scheduler may return various types of errors. Consider preemption only if
	// the error is of type FitError.
	fitError, ok := scheduleErr.(*FitError)
	if !ok || fitError == nil {
		return nil, nil, nil, nil
	}
	if !podEligibleToPreemptOthers(pod, g.nodeInfoSnapshot.NodeInfos(), g.enableNonPreempting) {
		klog.V(5).Infof("Pod %v/%v is not eligible for more preemption.", pod.Namespace, pod.Name)
		return nil, nil, nil, nil
	}
	allNodes, err := g.nodeInfoSnapshot.NodeInfos().List()
	if err != nil {
		return nil, nil, nil, err
	}
	if len(allNodes) == 0 {
		return nil, nil, nil, ErrNoNodesAvailable
	}
	potentialNodes := nodesWherePreemptionMightHelp(allNodes, fitError)
	if len(potentialNodes) == 0 {
		klog.V(3).Infof("Preemption will not help schedule pod %v/%v on any node.", pod.Namespace, pod.Name)
		// In this case, we should clean-up any existing nominated node name of the pod.
		return nil, nil, []*v1.Pod{pod}, nil
	}
	var pdbs []*policy.PodDisruptionBudget
	if g.pdbLister != nil {
		pdbs, err = g.pdbLister.List(labels.Everything())
		if err != nil {
			return nil, nil, nil, err
		}
	}
	nodeToVictims, err := g.selectNodesForPreemption(ctx, prof, state, pod, potentialNodes, pdbs)
	if err != nil {
		return nil, nil, nil, err
	}

	// We will only check nodeToVictims with extenders that support preemption.
	// Extenders which do not support preemption may later prevent preemptor from being scheduled on the nominated
	// node. In that case, scheduler will find a different host for the preemptor in subsequent scheduling cycles.
	nodeToVictims, err = g.processPreemptionWithExtenders(pod, nodeToVictims)
	if err != nil {
		return nil, nil, nil, err
	}

	candidateNode := pickOneNodeForPreemption(nodeToVictims)
	if candidateNode == nil {
		return nil, nil, nil, nil
	}

	// Lower priority pods nominated to run on this node, may no longer fit on
	// this node. So, we should remove their nomination. Removing their
	// nomination updates these pods and moves them to the active queue. It
	// lets scheduler find another place for them.
	nominatedPods := g.getLowerPriorityNominatedPods(pod, candidateNode.Name)
	return candidateNode, nodeToVictims[candidateNode].Pods, nominatedPods, nil
}

以上方法的逻辑是：
1）选择一个node对于这个抢占pod，注意这里和scheduler 的调度逻辑完全不同了。是通过PDB中断实现的。这个node的选择是一个并行的过程。
2）找到候选节点，继续给pickOneNodeForPreemption筛选。
3）最后也会返回低优先级的那个pod

完成抢占