共计 11547 个字符，预计需要花费 29 分钟才能阅读完成。
本篇内容主要讲解“怎么创建 Node Controller”，感兴趣的朋友不妨来看看。本文介绍的方法操作简单快捷，实用性强。下面就让丸趣 TV 小编来带大家学习“怎么创建 Node Controller”吧!
NewNodeController 入口
Controller Manager 在启动时，会启动一系列的 Controller，Node Controller 也是在 Controller Manager 启动时 StartControllers 方法中启动的 Controller 之一，其对应的创建代码如下。
cmd/kube-controller-manager/app/controllermanager.go:455
nodeController, err := nodecontroller.NewNodeController(sharedInformers.Core().V1().Pods(),
sharedInformers.Core().V1().Nodes(),
sharedInformers.Extensions().V1beta1().DaemonSets(),
cloud,
clientBuilder.ClientOrDie(node-controller),
s.PodEvictionTimeout.Duration,
s.NodeEvictionRate,
s.SecondaryNodeEvictionRate,
s.LargeClusterSizeThreshold,
s.UnhealthyZoneThreshold,
s.NodeMonitorGracePeriod.Duration,
s.NodeStartupGracePeriod.Duration,
s.NodeMonitorPeriod.Duration,
clusterCIDR,
serviceCIDR,
int(s.NodeCIDRMaskSize),
s.AllocateNodeCIDRs,
s.EnableTaintManager,
utilfeature.DefaultFeatureGate.Enabled(features.TaintBasedEvictions),
)可见,Node Controller 主要是 ListWatch sharedInformers 中的如下对象：
Pods
Nodes
DaemonSets
另外，需要注意：
s.EnableTaintManager 的默认值为 true，即表示默认开启 Taint Manager，可通过 –enable-taint-manager 进行设置。
DefaultFeatureGate.Enabled(features.TaintBasedEvictions) 的默认值为 false，可通过 –feature-gates 中添加 TaintBasedEvictions=true 修改为 true，true 即表示 Node 上的 Pods Eviction Operation 通过 TaintManager 来进行。
补充：关于 Kubernetes 的 Default FeaturesGate 的设置见如下代码：
pkg/features/kube_features.go:100
var defaultKubernetesFeatureGates = map[utilfeature.Feature]utilfeature.FeatureSpec{ExternalTrafficLocalOnly: {Default: true, PreRelease: utilfeature.Beta},
AppArmor: {Default: true, PreRelease: utilfeature.Beta},
DynamicKubeletConfig: {Default: false, PreRelease: utilfeature.Alpha},
DynamicVolumeProvisioning: {Default: true, PreRelease: utilfeature.Alpha},
ExperimentalHostUserNamespaceDefaultingGate: {Default: false, PreRelease: utilfeature.Beta},
ExperimentalCriticalPodAnnotation: {Default: false, PreRelease: utilfeature.Alpha},
AffinityInAnnotations: {Default: false, PreRelease: utilfeature.Alpha},
Accelerators: {Default: false, PreRelease: utilfeature.Alpha},
TaintBasedEvictions: {Default: false, PreRelease: utilfeature.Alpha},
// inherited features from generic apiserver, relisted here to get a conflict if it is changed
// unintentionally on either side:
StreamingProxyRedirects: {Default: true, PreRelease: utilfeature.Beta},
}NewNodeController 定义
func NewNodeController(
podInformer coreinformers.PodInformer,
nodeInformer coreinformers.NodeInformer,
daemonSetInformer extensionsinformers.DaemonSetInformer,
cloud cloudprovider.Interface,
kubeClient clientset.Interface,
podEvictionTimeout time.Duration,
evictionLimiterQPS float32,
secondaryEvictionLimiterQPS float32,
largeClusterThreshold int32,
unhealthyZoneThreshold float32,
nodeMonitorGracePeriod time.Duration,
nodeStartupGracePeriod time.Duration,
nodeMonitorPeriod time.Duration,
clusterCIDR *net.IPNet,
serviceCIDR *net.IPNet,
nodeCIDRMaskSize int,
allocateNodeCIDRs bool,
runTaintManager bool,
useTaintBasedEvictions bool) (*NodeController, error) {
nc := NodeController{
cloud: cloud,
knownNodeSet: make(map[string]*v1.Node),
kubeClient: kubeClient,
recorder: recorder,
podEvictionTimeout: podEvictionTimeout,
maximumGracePeriod: 5 * time.Minute, // 不可配置，表示 The maximum duration before a pod evicted from a node can be forcefully terminated
zonePodEvictor: make(map[string]*RateLimitedTimedQueue),
zoneNotReadyOrUnreachableTainer: make(map[string]*RateLimitedTimedQueue),
nodeStatusMap: make(map[string]nodeStatusData),
nodeMonitorGracePeriod: nodeMonitorGracePeriod,
nodeMonitorPeriod: nodeMonitorPeriod,
nodeStartupGracePeriod: nodeStartupGracePeriod,
lookupIP: net.LookupIP,
now: metav1.Now,
clusterCIDR: clusterCIDR,
serviceCIDR: serviceCIDR,
allocateNodeCIDRs: allocateNodeCIDRs,
forcefullyDeletePod: func(p *v1.Pod) error { return forcefullyDeletePod(kubeClient, p) },
nodeExistsInCloudProvider: func(nodeName types.NodeName) (bool, error) { return nodeExistsInCloudProvider(cloud, nodeName) },
evictionLimiterQPS: evictionLimiterQPS,
secondaryEvictionLimiterQPS: secondaryEvictionLimiterQPS,
largeClusterThreshold: largeClusterThreshold,
unhealthyZoneThreshold: unhealthyZoneThreshold,
zoneStates: make(map[string]zoneState),
runTaintManager: runTaintManager,
useTaintBasedEvictions: useTaintBasedEvictions runTaintManager,
// 注册 enterPartialDisruptionFunc 函数为 ReducedQPSFunc，当 zone state 为 PartialDisruption 时，将 invoke ReducedQPSFunc 来 setLimiterInZone。nc.enterPartialDisruptionFunc = nc.ReducedQPSFunc
// 注册 enterFullDisruptionFunc 函数为 HealthyQPSFunc，当 zone state 为 FullDisruption 时，将 invoke HealthyQPSFunc 来 setLimiterInZone。nc.enterFullDisruptionFunc = nc.HealthyQPSFunc
// 注册 computeZoneStateFunc 函数为 ComputeZoneState，当 handleDisruption 时，将 invoke ComputeZoneState 来计算集群中 unhealthy node number 及 zone state。nc.computeZoneStateFunc = nc.ComputeZoneState
// 注册 PodInformer 的 Event Handler：Add，Update，Delete。podInformer.Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
// 对于 Pod Add 和 Update Event，都会去判断 Node 上 kubelet 的 version，如果 version 低于 1.1.0，则会通过 forcefullyDeletePod 直接调用 apiserver 接口删除 etcd 中该 Pod object。 // 对于 Pod Add, Update, Delete Event，如果启动了 TaintManager，则会对比 OldPod 和 newPod 的 Tolerations 信息，如果不相同，则会将该 Pod 的变更信息 Add 到 NoExecuteTaintManager 的 podUpdateQueue 中，交给 Taint Controller 处理。只不过对于 Delete Event，newPod 为 nil。AddFunc: func(obj interface{}) {nc.maybeDeleteTerminatingPod(obj)
pod := obj.(*v1.Pod)
if nc.taintManager != nil {nc.taintManager.PodUpdated(nil, pod)
UpdateFunc: func(prev, obj interface{}) {nc.maybeDeleteTerminatingPod(obj)
prevPod := prev.(*v1.Pod)
newPod := obj.(*v1.Pod)
if nc.taintManager != nil {nc.taintManager.PodUpdated(prevPod, newPod)
DeleteFunc: func(obj interface{}) {pod, isPod := obj.(*v1.Pod)
// We can get DeletedFinalStateUnknown instead of *v1.Node here and we need to handle that correctly. #34692
if !isPod {deletedState, ok := obj.(cache.DeletedFinalStateUnknown)
if !ok {glog.Errorf( Received unexpected object: %v , obj)
return
pod, ok = deletedState.Obj.(*v1.Pod)
if !ok {glog.Errorf( DeletedFinalStateUnknown contained non-Node object: %v , deletedState.Obj)
return
if nc.taintManager != nil {nc.taintManager.PodUpdated(pod, nil)
// returns true if the shared informer s store has synced.
nc.podInformerSynced = podInformer.Informer().HasSynced
// 注册 NodeInformer 的 Event Handler：Add，Update，Delete。nodeEventHandlerFuncs := cache.ResourceEventHandlerFuncs{}
if nc.allocateNodeCIDRs { // --allocate-node-cidrs —— Should CIDRs for Pods be allocated and set on the cloud provider。} else {
nodeEventHandlerFuncs = cache.ResourceEventHandlerFuncs{
// 对于 Node Add, Update, Delete Event，如果启动了 TaintManager，则会对比 OldNode 和 newNode 的 Taints 信息，如果不相同，则会将该 Node 的变更信息 Add 到 NoExecuteTaintManager 的 nodeUpdateQueue 中，交给 Taint Controller 处理。只不过对于 Delete Event，newNode 为 nil。AddFunc: func(originalObj interface{}) {obj, err := api.Scheme.DeepCopy(originalObj)
if err != nil {utilruntime.HandleError(err)
return
node := obj.(*v1.Node)
if nc.taintManager != nil {nc.taintManager.NodeUpdated(nil, node)
UpdateFunc: func(oldNode, newNode interface{}) {node := newNode.(*v1.Node)
prevNode := oldNode.(*v1.Node)
if nc.taintManager != nil {nc.taintManager.NodeUpdated(prevNode, node)
DeleteFunc: func(originalObj interface{}) {obj, err := api.Scheme.DeepCopy(originalObj)
if err != nil {utilruntime.HandleError(err)
return
node, isNode := obj.(*v1.Node)
// We can get DeletedFinalStateUnknown instead of *v1.Node here and we need to handle that correctly. #34692
if !isNode {deletedState, ok := obj.(cache.DeletedFinalStateUnknown)
if !ok {glog.Errorf( Received unexpected object: %v , obj)
return
node, ok = deletedState.Obj.(*v1.Node)
if !ok {glog.Errorf( DeletedFinalStateUnknown contained non-Node object: %v , deletedState.Obj)
return
if nc.taintManager != nil {nc.taintManager.NodeUpdated(node, nil)
// 注册 NoExecuteTaintManager 为 taintManager。if nc.runTaintManager {nc.taintManager = NewNoExecuteTaintManager(kubeClient)
nodeInformer.Informer().AddEventHandler(nodeEventHandlerFuncs)
nc.nodeLister = nodeInformer.Lister()
// returns true if the shared informer s nodeStore has synced.
nc.nodeInformerSynced = nodeInformer.Informer().HasSynced
// returns true if the shared informer s daemonSetStore has synced.
nc.daemonSetStore = daemonSetInformer.Lister()
nc.daemonSetInformerSynced = daemonSetInformer.Informer().HasSynced
return nc, nil因此，创建 NodeController 实例时，主要进行了如下工作：
maximumGracePeriod – The maximum duration before a pod evicted from a node can be forcefully terminated. 不可配置，代码中写死为 5min。
注册 enterPartialDisruptionFunc 函数为 ReducedQPSFunc，当 zone state 为 PartialDisruption 时，将 invoke ReducedQPSFunc 来 setLimiterInZone。
注册 enterFullDisruptionFunc 函数为 HealthyQPSFunc，当 zone state 为 FullDisruption 时，将 invoke HealthyQPSFunc 来 setLimiterInZone。
注册 computeZoneStateFunc 函数为 ComputeZoneState，当 handleDisruption 时，将 invoke ComputeZoneState 来计算集群中 unhealthy node number 及 zone state。
注册 **PodInformer** 的 Event Handler：Add，Update，Delete。
对于 Pod Add 和 Update Event，都会去判断 Node 上 kubelet version，如果 version 低于 1.1.0，则会通过 forcefullyDeletePod 直接调用 apiserver 接口删除 etcd 中该 Pod object。
对于 Pod Add, Update, Delete Event，如果启动了 TaintManager，则会对比 OldPod 和 newPod 的 Tolerations 信息，如果不相同，则会将该 Pod 的变更信息 Add 到 NoExecuteTaintManager 的 **podUpdateQueue** 中，交给 Taint Controller 处理。只不过对于 Delete Event，newPod 为 nil。
注册 PodInformerSynced，用来检查 the shared informer s Podstore 是否已经 synced.
注册 **NodeInformer** 的 Event Handler：Add，Update，Delete。
对于 Node Add, Update, Delete Event，如果启动了 TaintManager，则会对比 OldNode 和 newNode 的 Taints 信息，如果不相同，则会将该 Node 的变更信息 Add 到 NoExecuteTaintManager 的 nodeUpdateQueue 中，交给 Taint Controller 处理。只不过对于 Delete Event，newNode 为 nil。
注册 NoExecuteTaintManager 为 taintManager。
注册 NodeInformerSynced，用来检查 the shared informer s NodeStore 是否已经 synced.
注册 DaemonSetInformerSynced，用来检查 the shared informer s DaemonSetStore 是否已经 synced.
关于 ZoneState
上面提到 ZoneState，关于 ZoneState 是怎么来的，见如下代码：
pkg/api/v1/types.go:3277
const (
// NodeReady means kubelet is healthy and ready to accept pods.
NodeReady NodeConditionType = Ready
// NodeOutOfDisk means the kubelet will not accept new pods due to insufficient free disk
// space on the node.
NodeOutOfDisk NodeConditionType = OutOfDisk
// NodeMemoryPressure means the kubelet is under pressure due to insufficient available memory.
NodeMemoryPressure NodeConditionType = MemoryPressure
// NodeDiskPressure means the kubelet is under pressure due to insufficient available disk.
NodeDiskPressure NodeConditionType = DiskPressure
// NodeNetworkUnavailable means that network for the node is not correctly configured.
NodeNetworkUnavailable NodeConditionType = NetworkUnavailable
// NodeInodePressure means the kubelet is under pressure due to insufficient available inodes.
NodeInodePressure NodeConditionType = InodePressure
// This function is expected to get a slice of NodeReadyConditions for all Nodes in a given zone.
// The zone is considered:
// - fullyDisrupted if there re no Ready Nodes,
// - partiallyDisrupted if at least than nc.unhealthyZoneThreshold percent of Nodes are not Ready,
// - normal otherwise
func (nc *NodeController) ComputeZoneState(nodeReadyConditions []*v1.NodeCondition) (int, zoneState) {
readyNodes := 0
notReadyNodes := 0
for i := range nodeReadyConditions {if nodeReadyConditions[i] != nil nodeReadyConditions[i].Status == v1.ConditionTrue {readyNodes++} else {
notReadyNodes++
switch {
case readyNodes == 0 notReadyNodes 0:
return notReadyNodes, stateFullDisruption
case notReadyNodes 2 float32(notReadyNodes)/float32(notReadyNodes+readyNodes) = nc.unhealthyZoneThreshold:
return notReadyNodes, statePartialDisruption
default:
return notReadyNodes, stateNormal
}zone state 共分为如下三种类型：
FullDisruption：Ready 状态的 Nodes number 为 0，并且 NotReady 状态的 Nodes number 大于 0。
PartialDisruption：NotReady 状态的 Nodes number 大于 2，并且 notReadyNodes/(notReadyNodes+readyNodes) = nc.unhealthyZoneThreshold, 其中 nc.unhealthyZoneThreshold 通过 –unhealthy-zone-threshold 设置，默认为 0.55。
Normal：除了以上两种 zone state，其他都属于 Normal 状态。
到此，相信大家对“怎么创建 Node Controller”有了更深的了解，不妨来实际操作一番吧！这里是丸趣 TV 网站，更多相关内容可以进入相关频道进行查询，关注我们，继续学习！
