原 荐 Kubernetes HPA Con

cmd/kube-controller-manager/app/autoscaling.go    // HPA Controller的启动代码


/pkg/controller/podautoscaler
.
├── BUILD
├── OWNERS
├── doc.go
├── horizontal.go    // podautoscaler的核心代码，包括其创建和运行的代码
├── horizontal_test.go
├── metrics
│   ├── BUILD
│   ├── metrics_client.go
│   ├── metrics_client_test.go
│   ├── metrics_client_test.go.orig
│   ├── metrics_client_test.go.rej
│   └── utilization.go
├── replica_calculator.go   // ReplicaCaculator的创建，以及根据cpu/metrics计算replicas的方法
└── replica_calculator_test.go

cmd/kube-controller-manager/app/controllermanager.go:224

func newControllerInitializers() map[string]InitFunc {
	controllers := map[string]InitFunc{}
	
	...
	
	controllers["horizontalpodautoscaling"] = startHPAController
	
	...

	return controllers
}

cmd/kube-controller-manager/app/autoscaling.go:29

func startHPAController(ctx ControllerContext) (bool, error) {
	
	...
	
	// HPA Controller需要集群已经部署Heapster，由Heapster提供监控数据，来进行replicas的计算。
	metricsClient := metrics.NewHeapsterMetricsClient(
		hpaClient,
		metrics.DefaultHeapsterNamespace,
		metrics.DefaultHeapsterScheme,
		metrics.DefaultHeapsterService,
		metrics.DefaultHeapsterPort,
	)
	
	// 创建ReplicaCaculator，后面会用它来计算desired replicas。
	replicaCalc := podautoscaler.NewReplicaCalculator(metricsClient, hpaClient.Core())
	
	// 创建HPA Controller，并启动goroutine执行其Run方法，开始工作。
	go podautoscaler.NewHorizontalController(
		hpaClient.Core(),
		hpaClient.Extensions(),
		hpaClient.Autoscaling(),
		replicaCalc,
		ctx.Options.HorizontalPodAutoscalerSyncPeriod.Duration,
	).Run(ctx.Stop)
	
	return true, nil
}

pkg/controller/podautoscaler/horizontal.go:112

func NewHorizontalController(evtNamespacer v1core.EventsGetter, scaleNamespacer unversionedextensions.ScalesGetter, hpaNamespacer unversionedautoscaling.HorizontalPodAutoscalersGetter, replicaCalc *ReplicaCalculator, resyncPeriod time.Duration) *HorizontalController {
	
	...

	// 构建HPA Controller
	controller := &HorizontalController{
		replicaCalc:     replicaCalc,
		eventRecorder:   recorder,
		scaleNamespacer: scaleNamespacer,
		hpaNamespacer:   hpaNamespacer,
	}
	
	// 创建Informer，配置对应的ListWatch Func，及其对应的EventHandler，用来监控HPA Resource的Add和Update事件。newInformer是HPA的核心代码入口。
	store, frameworkController := newInformer(controller, resyncPeriod)
	controller.store = store
	controller.controller = frameworkController

	return controller
}

pkg/controller/podautoscaler/horizontal.go:59

type HorizontalController struct {
	scaleNamespacer unversionedextensions.ScalesGetter
	hpaNamespacer   unversionedautoscaling.HorizontalPodAutoscalersGetter

	replicaCalc   *ReplicaCalculator
	eventRecorder record.EventRecorder

	// A store of HPA objects, populated by the controller.
	store cache.Store
	// Watches changes to all HPA objects.
	controller *cache.Controller
}

pkg/apis/extensions/v1beta1/types.go:56

// represents a scaling request for a resource.
type Scale struct {
	metav1.TypeMeta `json:",inline"`
	// Standard object metadata; More info: http://releases.k8s.io/HEAD/docs/devel/api-conventions.md#metadata.
	// +optional
	v1.ObjectMeta `json:"metadata,omitempty" protobuf:"bytes,1,opt,name=metadata"`

	// defines the behavior of the scale. More info: http://releases.k8s.io/HEAD/docs/devel/api-conventions.md#spec-and-status.
	// +optional
	Spec ScaleSpec `json:"spec,omitempty" protobuf:"bytes,2,opt,name=spec"`

	// current status of the scale. More info: http://releases.k8s.io/HEAD/docs/devel/api-conventions.md#spec-and-status. Read-only.
	// +optional
	Status ScaleStatus `json:"status,omitempty" protobuf:"bytes,3,opt,name=status"`
}

// describes the attributes of a scale subresource
type ScaleSpec struct {
	// desired number of instances for the scaled object.
	Replicas int `json:"replicas,omitempty"`
}

// represents the current status of a scale subresource.
type ScaleStatus struct {
	// actual number of observed instances of the scaled object.
	Replicas int `json:"replicas"`

	// label query over pods that should match the replicas count.
	Selector map[string]string `json:"selector,omitempty"`
}

pkg/controller/podautoscaler/horizontal.go:75

func newInformer(controller *HorizontalController, resyncPeriod time.Duration) (cache.Store, *cache.Controller) {
	return cache.NewInformer(
	
		// 配置ListFucn和WatchFunc，用来定期List和watch HPA resource。
		&cache.ListWatch{
			ListFunc: func(options v1.ListOptions) (runtime.Object, error) {
				return controller.hpaNamespacer.HorizontalPodAutoscalers(v1.NamespaceAll).List(options)
			},
			WatchFunc: func(options v1.ListOptions) (watch.Interface, error) {
				return controller.hpaNamespacer.HorizontalPodAutoscalers(v1.NamespaceAll).Watch(options)
			},
		},
		
		// 定义期望收到的object为HorizontalPodAutoscaler
		&autoscaling.HorizontalPodAutoscaler{},
		
		// 定义定期List的周期
		resyncPeriod,
		
		// 配置HPA resource event的Handler（AddFunc, UpdateFunc）
		cache.ResourceEventHandlerFuncs{
			AddFunc: func(obj interface{}) {
				hpa := obj.(*autoscaling.HorizontalPodAutoscaler)
				hasCPUPolicy := hpa.Spec.TargetCPUUtilizationPercentage != nil
				_, hasCustomMetricsPolicy := hpa.Annotations[HpaCustomMetricsTargetAnnotationName]
				if !hasCPUPolicy && !hasCustomMetricsPolicy {
					controller.eventRecorder.Event(hpa, v1.EventTypeNormal, "DefaultPolicy", "No scaling policy specified - will use default one. See documentation for details")
				}
				
				// 根据监控调整hpa的数据
				err := controller.reconcileAutoscaler(hpa)
				if err != nil {
					glog.Warningf("Failed to reconcile %s: %v", hpa.Name, err)
				}
			},
			UpdateFunc: func(old, cur interface{}) {
				hpa := cur.(*autoscaling.HorizontalPodAutoscaler)
				
				// 根据监控调整hpa的数据
				err := controller.reconcileAutoscaler(hpa)
				if err != nil {
					glog.Warningf("Failed to reconcile %s: %v", hpa.Name, err)
				}
			},
			// We are not interested in deletions.
		},
	)
}

pkg/apis/autoscaling/v1/types.go:76

// configuration of a horizontal pod autoscaler.
type HorizontalPodAutoscaler struct {
	metav1.TypeMeta `json:",inline"`
	// Standard object metadata. More info: http://releases.k8s.io/HEAD/docs/devel/api-conventions.md#metadata
	// +optional
	v1.ObjectMeta `json:"metadata,omitempty" protobuf:"bytes,1,opt,name=metadata"`

	// behaviour of autoscaler. More info: http://releases.k8s.io/HEAD/docs/devel/api-conventions.md#spec-and-status.
	// +optional
	Spec HorizontalPodAutoscalerSpec `json:"spec,omitempty" protobuf:"bytes,2,opt,name=spec"`

	// current information about the autoscaler.
	// +optional
	Status HorizontalPodAutoscalerStatus `json:"status,omitempty" protobuf:"bytes,3,opt,name=status"`
}

pkg/controller/podautoscaler/horizontal.go:272

func (a *HorizontalController) reconcileAutoscaler(hpa *autoscaling.HorizontalPodAutoscaler) error {
	...

	// 获取对应resource的scale subresource数据。
	scale, err := a.scaleNamespacer.Scales(hpa.Namespace).Get(hpa.Spec.ScaleTargetRef.Kind, hpa.Spec.ScaleTargetRef.Name)
	
	...
	
	// 得到当前副本数
	currentReplicas := scale.Status.Replicas

	cpuDesiredReplicas := int32(0)
	cpuCurrentUtilization := new(int32)
	cpuTimestamp := time.Time{}

	cmDesiredReplicas := int32(0)
	cmMetric := ""
	cmStatus := ""
	cmTimestamp := time.Time{}

	desiredReplicas := int32(0)
	rescaleReason := ""
	timestamp := time.Now()

	rescale := true

	// 如果期望副本数为0，这不进行scale操作。
	if scale.Spec.Replicas == 0 {
		// Autoscaling is disabled for this resource
		desiredReplicas = 0
		rescale = false
	} 
	
	// 期望副本数不能超过hpa中配置的最大副本数
	else if currentReplicas > hpa.Spec.MaxReplicas {
		rescaleReason = "Current number of replicas above Spec.MaxReplicas"
		desiredReplicas = hpa.Spec.MaxReplicas
	} 
	
	// 期望副本数不能低于配置的最小副本数
	else if hpa.Spec.MinReplicas != nil && currentReplicas < *hpa.Spec.MinReplicas {
		rescaleReason = "Current number of replicas below Spec.MinReplicas"
		desiredReplicas = *hpa.Spec.MinReplicas
	} 
	
	// 期望副本数最少为1
	else if currentReplicas == 0 {
		rescaleReason = "Current number of replicas must be greater than 0"
		desiredReplicas = 1
	} 
	// 如果当前副本数在Min和Max之间，则需要根据cpu或者custom metrics（如果加了对应的Annotation）数据进行算法计算得到期望副本数。
	else {
		// All basic scenarios covered, the state should be sane, lets use metrics.
		cmAnnotation, cmAnnotationFound := hpa.Annotations[HpaCustomMetricsTargetAnnotationName]

		if hpa.Spec.TargetCPUUtilizationPercentage != nil || !cmAnnotationFound {
		
			// 根据cpu利用率计算期望副本数
			cpuDesiredReplicas, cpuCurrentUtilization, cpuTimestamp, err = a.computeReplicasForCPUUtilization(hpa, scale)
			if err != nil {
			
				// 更新hpa的当前副本数
				a.updateCurrentReplicasInStatus(hpa, currentReplicas)
				return fmt.Errorf("failed to compute desired number of replicas based on CPU utilization for %s: %v", reference, err)
			}
		}

		if cmAnnotationFound {
		
			// 根据custom metrics数据计算期望副本数
			cmDesiredReplicas, cmMetric, cmStatus, cmTimestamp, err = a.computeReplicasForCustomMetrics(hpa, scale, cmAnnotation)
			if err != nil {
			
				// 更新hpa的当前副本数
				a.updateCurrentReplicasInStatus(hpa, currentReplicas)
				return fmt.Errorf("failed to compute desired number of replicas based on Custom Metrics for %s: %v", reference, err)
			}
		}

		// 取cpu和custom metric得到的期望副本数的最大值作为最终的desired replicas，并且要在min和max范围内。
		rescaleMetric := ""
		if cpuDesiredReplicas > desiredReplicas {
			desiredReplicas = cpuDesiredReplicas
			timestamp = cpuTimestamp
			rescaleMetric = "CPU utilization"
		}
		if cmDesiredReplicas > desiredReplicas {
			desiredReplicas = cmDesiredReplicas
			timestamp = cmTimestamp
			rescaleMetric = cmMetric
		}
		if desiredReplicas > currentReplicas {
			rescaleReason = fmt.Sprintf("%s above target", rescaleMetric)
		}
		if desiredReplicas < currentReplicas {
			rescaleReason = "All metrics below target"
		}

		if hpa.Spec.MinReplicas != nil && desiredReplicas < *hpa.Spec.MinReplicas {
			desiredReplicas = *hpa.Spec.MinReplicas
		}

		//  never scale down to 0, reserved for disabling autoscaling
		if desiredReplicas == 0 {
			desiredReplicas = 1
		}

		if desiredReplicas > hpa.Spec.MaxReplicas {
			desiredReplicas = hpa.Spec.MaxReplicas
		}

		// Do not upscale too much to prevent incorrect rapid increase of the number of master replicas caused by
		// bogus CPU usage report from heapster/kubelet (like in issue #32304).
		if desiredReplicas > calculateScaleUpLimit(currentReplicas) {
			desiredReplicas = calculateScaleUpLimit(currentReplicas)
		}

		// 根据currentReplicas和desiredReplicas的对比，以及scale时间是否满足配置间隔要求，决定是否此时需要rescale
		rescale = shouldScale(hpa, currentReplicas, desiredReplicas, timestamp)
	}

	if rescale {
		scale.Spec.Replicas = desiredReplicas
		// 执行ScaleInterface的Update接口，触发调用API Server的对应resource的scale subresource的数据更新。其实最终会去修改对应rc或者deployment的replicas，然后由rc或deployment Controller去最终扩容或者缩容，使得副本数达到新的期望值。
		_, err = a.scaleNamespacer.Scales(hpa.Namespace).Update(hpa.Spec.ScaleTargetRef.Kind, scale)
		if err != nil {
			a.eventRecorder.Eventf(hpa, v1.EventTypeWarning, "FailedRescale", "New size: %d; reason: %s; error: %v", desiredReplicas, rescaleReason, err.Error())
			return fmt.Errorf("failed to rescale %s: %v", reference, err)
		}
		a.eventRecorder.Eventf(hpa, v1.EventTypeNormal, "SuccessfulRescale", "New size: %d; reason: %s", desiredReplicas, rescaleReason)
		glog.Infof("Successfull rescale of %s, old size: %d, new size: %d, reason: %s",
			hpa.Name, currentReplicas, desiredReplicas, rescaleReason)
	} else {
		desiredReplicas = currentReplicas
	}

	// 更新hpa resource的status数据
	return a.updateStatus(hpa, currentReplicas, desiredReplicas, cpuCurrentUtilization, cmStatus, rescale)
}

pkg/controller/podautoscaler/horizontal.go:387

...

var downscaleForbiddenWindow = 5 * time.Minute
var upscaleForbiddenWindow = 3 * time.Minute

...

func shouldScale(hpa *autoscaling.HorizontalPodAutoscaler, currentReplicas, desiredReplicas int32, timestamp time.Time) bool {
	if desiredReplicas == currentReplicas {
		return false
	}

	if hpa.Status.LastScaleTime == nil {
		return true
	}

	// Going down only if the usageRatio dropped significantly below the target
	// and there was no rescaling in the last downscaleForbiddenWindow.
	if desiredReplicas < currentReplicas && hpa.Status.LastScaleTime.Add(downscaleForbiddenWindow).Before(timestamp) {
		return true
	}

	// Going up only if the usage ratio increased significantly above the target
	// and there was no rescaling in the last upscaleForbiddenWindow.
	if desiredReplicas > currentReplicas && hpa.Status.LastScaleTime.Add(upscaleForbiddenWindow).Before(timestamp) {
		return true
	}
	return false
}

pkg/registry/core/rest/storage_core.go:91
func (c LegacyRESTStorageProvider) NewLegacyRESTStorage(restOptionsGetter generic.RESTOptionsGetter) (LegacyRESTStorage, genericapiserver.APIGroupInfo, error) {
	...
	if autoscalingGroupVersion := (schema.GroupVersion{Group: "autoscaling", Version: "v1"}); registered.IsEnabledVersion(autoscalingGroupVersion) {
		apiGroupInfo.SubresourceGroupVersionKind["replicationcontrollers/scale"] = autoscalingGroupVersion.WithKind("Scale")
	}

	...
	restStorageMap := map[string]rest.Storage{
		...
		
		"replicationControllers":        controllerStorage.Controller,
		"replicationControllers/status": controllerStorage.Status,
		
		...
	}
	return restStorage, apiGroupInfo, nil
}



pkg/registry/core/controller/etcd/etcd.go:124

func (r *ScaleREST) Update(ctx api.Context, name string, objInfo rest.UpdatedObjectInfo) (runtime.Object, bool, error) {
	rc, err := r.registry.GetController(ctx, name, &metav1.GetOptions{})
	if err != nil {
		return nil, false, errors.NewNotFound(autoscaling.Resource("replicationcontrollers/scale"), name)
	}

	oldScale := scaleFromRC(rc)
	obj, err := objInfo.UpdatedObject(ctx, oldScale)
	if err != nil {
		return nil, false, err
	}

	if obj == nil {
		return nil, false, errors.NewBadRequest("nil update passed to Scale")
	}
	scale, ok := obj.(*autoscaling.Scale)
	if !ok {
		return nil, false, errors.NewBadRequest(fmt.Sprintf("wrong object passed to Scale update: %v", obj))
	}

	if errs := validation.ValidateScale(scale); len(errs) > 0 {
		return nil, false, errors.NewInvalid(autoscaling.Kind("Scale"), scale.Name, errs)
	}
	
	// 设置rc对应spec.replicas为Scale中的期望副本数
	rc.Spec.Replicas = scale.Spec.Replicas
	rc.ResourceVersion = scale.ResourceVersion
	
	// 更新到etcd
	rc, err = r.registry.UpdateController(ctx, rc)
	if err != nil {
		return nil, false, err
	}
	return scaleFromRC(rc), false, nil
}

pkg/controller/podautoscaler/horizontal.go:130

func (a *HorizontalController) Run(stopCh <-chan struct{}) {
	defer utilruntime.HandleCrash()
	glog.Infof("Starting HPA Controller")
	go a.controller.Run(stopCh)
	<-stopCh
	glog.Infof("Shutting down HPA Controller")
}