Kubernetes22--kube-scheduler源码7--预选过程分析

kubernetes/pkg/scheduler/core/generic_scheduler.go

从一系列Node列表中为某一Pod选择最合适的Node节点

func (g *genericScheduler) Schedule(pod *v1.Pod, nodeLister algorithm.NodeLister) (string, error)

预选过程入口

func (g *genericScheduler) findNodesThatFit(pod *v1.Pod, nodes []*v1.Node) ([]*v1.Node, FailedPredicateMap, error)

在一系列预选策略下判断某一Node是否满足该Pod对象预选条件

func podFitsOnNode(
	pod *v1.Pod,
	meta algorithm.PredicateMetadata,
	info *schedulercache.NodeInfo,
	predicateFuncs map[string]algorithm.FitPredicate,
	nodeCache *equivalence.NodeCache,
	queue internalqueue.SchedulingQueue,
	alwaysCheckAllPredicates bool,
	equivClass *equivalence.Class,
) (bool, []algorithm.PredicateFailureReason, error)

接下来调用

type FitPredicate func(pod *v1.Pod, meta PredicateMetadata, nodeInfo *schedulercache.NodeInfo) (bool, []PredicateFailureReason, error)

FitPredicate具体实现： kubernetes/pkg/scheduler/algorithm/predicates/predicates.go

默认支持预选策略

var (
	predicatesOrdering = []string{CheckNodeConditionPred, CheckNodeUnschedulablePred,
		GeneralPred, HostNamePred, PodFitsHostPortsPred,
		MatchNodeSelectorPred, PodFitsResourcesPred, NoDiskConflictPred,
		PodToleratesNodeTaintsPred, PodToleratesNodeNoExecuteTaintsPred, CheckNodeLabelPresencePred,
		CheckServiceAffinityPred, MaxEBSVolumeCountPred, MaxGCEPDVolumeCountPred, MaxCSIVolumeCountPred,
		MaxAzureDiskVolumeCountPred, CheckVolumeBindingPred, NoVolumeZoneConflictPred,
		CheckNodeMemoryPressurePred, CheckNodePIDPressurePred, CheckNodeDiskPressurePred, MatchInterPodAffinityPred}
)

defaultprovider初始化时定义了四种预选策略

// Fit is defined based on the absence of port conflicts.
	// This predicate is actually a default predicate, because it is invoked from
	// predicates.GeneralPredicates()
	factory.RegisterFitPredicate(predicates.PodFitsHostPortsPred, predicates.PodFitsHostPorts)
	// Fit is determined by resource availability.
	// This predicate is actually a default predicate, because it is invoked from
	// predicates.GeneralPredicates()
	factory.RegisterFitPredicate(predicates.PodFitsResourcesPred, predicates.PodFitsResources)
	// Fit is determined by the presence of the Host parameter and a string match
	// This predicate is actually a default predicate, because it is invoked from
	// predicates.GeneralPredicates()
	factory.RegisterFitPredicate(predicates.HostNamePred, predicates.PodFitsHost)
	// Fit is determined by node selector query.
	factory.RegisterFitPredicate(predicates.MatchNodeSelectorPred, predicates.PodMatchNodeSelector)

端口是否冲突PodFitsHostPorts

// PodFitsHostPorts checks if a node has free ports for the requested pod ports.
func PodFitsHostPorts(pod *v1.Pod, meta algorithm.PredicateMetadata, nodeInfo *schedulercache.NodeInfo) (bool, []algorithm.PredicateFailureReason, error) {
	var wantPorts []*v1.ContainerPort
	if predicateMeta, ok := meta.(*predicateMetadata); ok {
		wantPorts = predicateMeta.podPorts
	} else {
		// We couldn't parse metadata - fallback to computing it.
		wantPorts = schedutil.GetContainerPorts(pod)
	}
	if len(wantPorts) == 0 {
		return true, nil, nil
	}

	existingPorts := nodeInfo.UsedPorts()

	// try to see whether existingPorts and  wantPorts will conflict or not
	if portsConflict(existingPorts, wantPorts) {
		return false, []algorithm.PredicateFailureReason{ErrPodNotFitsHostPorts}, nil
	}

	return true, nil, nil
}

// GetContainerPorts returns the used host ports of Pods: if 'port' was used, a 'port:true' pair
// will be in the result; but it does not resolve port conflict.
func GetContainerPorts(pods ...*v1.Pod) []*v1.ContainerPort {
	var ports []*v1.ContainerPort
	for _, pod := range pods {
		for j := range pod.Spec.Containers {
			container := &pod.Spec.Containers[j]
			for k := range container.Ports {
				ports = append(ports, &container.Ports[k])
			}
		}
	}
	return ports
}

资源是否满足PodFitsResources

// PodFitsResources checks if a node has sufficient resources, such as cpu, memory, gpu, opaque int resources etc to run a pod.
// First return value indicates whether a node has sufficient resources to run a pod while the second return value indicates the
// predicate failure reasons if the node has insufficient resources to run the pod.
func PodFitsResources(pod *v1.Pod, meta algorithm.PredicateMetadata, nodeInfo *schedulercache.NodeInfo) (bool, []algorithm.PredicateFailureReason, error) {
	node := nodeInfo.Node()
	if node == nil {
		return false, nil, fmt.Errorf("node not found")
	}

	var predicateFails []algorithm.PredicateFailureReason
	allowedPodNumber := nodeInfo.AllowedPodNumber()
	if len(nodeInfo.Pods())+1 > allowedPodNumber {
		predicateFails = append(predicateFails, NewInsufficientResourceError(v1.ResourcePods, 1, int64(len(nodeInfo.Pods())), int64(allowedPodNumber)))
	}

	// No extended resources should be ignored by default.
	ignoredExtendedResources := sets.NewString()

	var podRequest *schedulercache.Resource
	if predicateMeta, ok := meta.(*predicateMetadata); ok {
		podRequest = predicateMeta.podRequest
		if predicateMeta.ignoredExtendedResources != nil {
			ignoredExtendedResources = predicateMeta.ignoredExtendedResources
		}
	} else {
		// We couldn't parse metadata - fallback to computing it.
		podRequest = GetResourceRequest(pod)
	}
	if podRequest.MilliCPU == 0 &&
		podRequest.Memory == 0 &&
		podRequest.EphemeralStorage == 0 &&
		len(podRequest.ScalarResources) == 0 {
		return len(predicateFails) == 0, predicateFails, nil
	}

	allocatable := nodeInfo.AllocatableResource()
	if allocatable.MilliCPU < podRequest.MilliCPU+nodeInfo.RequestedResource().MilliCPU {
		predicateFails = append(predicateFails, NewInsufficientResourceError(v1.ResourceCPU, podRequest.MilliCPU, nodeInfo.RequestedResource().MilliCPU, allocatable.MilliCPU))
	}
	if allocatable.Memory < podRequest.Memory+nodeInfo.RequestedResource().Memory {
		predicateFails = append(predicateFails, NewInsufficientResourceError(v1.ResourceMemory, podRequest.Memory, nodeInfo.RequestedResource().Memory, allocatable.Memory))
	}
	if allocatable.EphemeralStorage < podRequest.EphemeralStorage+nodeInfo.RequestedResource().EphemeralStorage {
		predicateFails = append(predicateFails, NewInsufficientResourceError(v1.ResourceEphemeralStorage, podRequest.EphemeralStorage, nodeInfo.RequestedResource().EphemeralStorage, allocatable.EphemeralStorage))
	}

	for rName, rQuant := range podRequest.ScalarResources {
		if v1helper.IsExtendedResourceName(rName) {
			// If this resource is one of the extended resources that should be
			// ignored, we will skip checking it.
			if ignoredExtendedResources.Has(string(rName)) {
				continue
			}
		}
		if allocatable.ScalarResources[rName] < rQuant+nodeInfo.RequestedResource().ScalarResources[rName] {
			predicateFails = append(predicateFails, NewInsufficientResourceError(rName, podRequest.ScalarResources[rName], nodeInfo.RequestedResource().ScalarResources[rName], allocatable.ScalarResources[rName]))
		}
	}

	if klog.V(10) {
		if len(predicateFails) == 0 {
			// We explicitly don't do klog.V(10).Infof() to avoid computing all the parameters if this is
			// not logged. There is visible performance gain from it.
			klog.Infof("Schedule Pod %+v on Node %+v is allowed, Node is running only %v out of %v Pods.",
				podName(pod), node.Name, len(nodeInfo.Pods()), allowedPodNumber)
		}
	}
	return len(predicateFails) == 0, predicateFails, nil
}

主机名是否符合PodFitsHost

// PodFitsHost checks if a pod spec node name matches the current node.
func PodFitsHost(pod *v1.Pod, meta algorithm.PredicateMetadata, nodeInfo *schedulercache.NodeInfo) (bool, []algorithm.PredicateFailureReason, error) {
	if len(pod.Spec.NodeName) == 0 {
		return true, nil, nil
	}
	node := nodeInfo.Node()
	if node == nil {
		return false, nil, fmt.Errorf("node not found")
	}
	if pod.Spec.NodeName == node.Name {
		return true, nil, nil
	}
	return false, []algorithm.PredicateFailureReason{ErrPodNotMatchHostName}, nil
}

nodeSelector标签是否符合

// PodMatchNodeSelector checks if a pod node selector matches the node label.
func PodMatchNodeSelector(pod *v1.Pod, meta algorithm.PredicateMetadata, nodeInfo *schedulercache.NodeInfo) (bool, []algorithm.PredicateFailureReason, error) {
	node := nodeInfo.Node()
	if node == nil {
		return false, nil, fmt.Errorf("node not found")
	}
	if podMatchesNodeSelectorAndAffinityTerms(pod, node) {
		return true, nil, nil
	}
	return false, []algorithm.PredicateFailureReason{ErrNodeSelectorNotMatch}, nil
}