溫馨提示×
您好，登錄后才能下訂單哦！
點擊 登錄注冊 即表示同意《億速云用戶服務條款》
您好，登錄后才能下訂單哦！
本篇內容主要講解“怎么創建Node Controller”，感興趣的朋友不妨來看看。本文介紹的方法操作簡單快捷，實用性強。下面就讓小編來帶大家學習“怎么創建Node Controller”吧!
Controller Manager在啟動時，會啟動一系列的Controller，Node Controller也是在Controller Manager啟動時StartControllers方法中啟動的Controller之一，其對應的創建代碼如下。
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),
)可見,Node Controller主要是ListWatch sharedInformers中的如下對象：
Pods
Nodes
DaemonSets
另外，需要注意：
s.EnableTaintManager的默認值為true，即表示默認開啟Taint Manager，可通過--enable-taint-manager進行設置。
DefaultFeatureGate.Enabled(features.TaintBasedEvictions)的默認值為false，可通過--feature-gates中添加TaintBasedEvictions=true修改為true，true即表示Node上的Pods Eviction Operation通過TaintManager來進行。
補充：關于Kubernetes的Default FeaturesGate的設置見如下代碼：
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},
}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,
}
...
// 注冊enterPartialDisruptionFunc函數為ReducedQPSFunc，當zone state為"PartialDisruption"時，將invoke ReducedQPSFunc來setLimiterInZone。
nc.enterPartialDisruptionFunc = nc.ReducedQPSFunc
// 注冊enterFullDisruptionFunc函數為HealthyQPSFunc，當zone state為"FullDisruption"時，將invoke HealthyQPSFunc來setLimiterInZone。
nc.enterFullDisruptionFunc = nc.HealthyQPSFunc
// 注冊computeZoneStateFunc函數為ComputeZoneState，當handleDisruption時，將invoke ComputeZoneState來計算集群中unhealthy node number及zone state。
nc.computeZoneStateFunc = nc.ComputeZoneState
// 注冊PodInformer的Event Handler：Add，Update，Delete。
podInformer.Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
// 對于Pod Add和Update Event，都會去判斷Node上kubelet的version，如果version低于1.1.0，則會通過forcefullyDeletePod直接調用apiserver接口刪除etcd中該Pod object。
// 對于Pod Add, Update, Delete Event，如果啟動了TaintManager，則會對比OldPod和newPod的Tolerations信息，如果不相同，則會將該Pod的變更信息Add到NoExecuteTaintManager的podUpdateQueue中，交給Taint Controller處理。只不過對于Delete Event，newPod 為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
// 注冊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{
// 對于Node Add, Update, Delete Event，如果啟動了TaintManager，則會對比OldNode和newNode的Taints信息，如果不相同，則會將該Node的變更信息Add到NoExecuteTaintManager的nodeUpdateQueue中，交給Taint Controller處理。只不過對于Delete Event，newNode 為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)
}
},
}
}
// 注冊NoExecuteTaintManager為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，創建NodeController實例時，主要進行了如下工作：
maximumGracePeriod - The maximum duration before a pod evicted from a node can be forcefully terminated. 不可配置，代碼中寫死為5min。
注冊enterPartialDisruptionFunc函數為ReducedQPSFunc，當zone state為"PartialDisruption"時，將invoke ReducedQPSFunc來setLimiterInZone。
注冊enterFullDisruptionFunc函數為HealthyQPSFunc，當zone state為"FullDisruption"時，將invoke HealthyQPSFunc來setLimiterInZone。
注冊computeZoneStateFunc函數為ComputeZoneState，當handleDisruption時，將invoke ComputeZoneState來計算集群中unhealthy node number及zone state。
注冊**PodInformer**的Event Handler：Add，Update，Delete。
對于Pod Add和Update Event，都會去判斷Node上kubelet version，如果version低于1.1.0，則會通過forcefullyDeletePod直接調用apiserver接口刪除etcd中該Pod object。
對于Pod Add, Update, Delete Event，如果啟動了TaintManager，則會對比OldPod和newPod的Tolerations信息，如果不相同，則會將該Pod的變更信息Add到NoExecuteTaintManager的**podUpdateQueue**中，交給Taint Controller處理。只不過對于Delete Event，newPod 為nil。
注冊PodInformerSynced，用來檢查the shared informer's Podstore 是否已經synced.
注冊**NodeInformer**的Event Handler：Add，Update，Delete。
對于Node Add, Update, Delete Event，如果啟動了TaintManager，則會對比OldNode和newNode的Taints信息，如果不相同，則會將該Node的變更信息Add到NoExecuteTaintManager的nodeUpdateQueue中，交給Taint Controller處理。只不過對于Delete Event，newNode 為nil。
注冊NoExecuteTaintManager為taintManager。
注冊NodeInformerSynced，用來檢查the shared informer's NodeStore 是否已經synced.
注冊DaemonSetInformerSynced，用來檢查the shared informer's DaemonSetStore 是否已經synced.
上面提到ZoneState，關于ZoneState是怎么來的，見如下代碼：
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"
)
pkg/controller/node/nodecontroller.go:1149
// 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共分為如下三種類型：
FullDisruption：Ready狀態的Nodes number為0，并且NotReady狀態的Nodes number大于0。
PartialDisruption：NotReady狀態的Nodes number大于2，并且notReadyNodes/(notReadyNodes+readyNodes) >= nc.unhealthyZoneThreshold,其中nc.unhealthyZoneThreshold通過--unhealthy-zone-threshold設置，默認為0.55。
Normal：除了以上兩種zone state，其他都屬于Normal狀態。
到此，相信大家對“怎么創建Node Controller”有了更深的了解，不妨來實際操作一番吧！這里是億速云網站，更多相關內容可以進入相關頻道進行查詢，關注我們，繼續學習！
免責聲明：本站發布的內容（圖片、視頻和文字）以原創、轉載和分享為主，文章觀點不代表本網站立場，如果涉及侵權請聯系站長郵箱：is@yisu.com進行舉報，并提供相關證據，一經查實，將立刻刪除涉嫌侵權內容。
