Cluster Autoscaler:集群自动扩缩容

apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  name: cluster-autoscaler
  namespace: kube-system
  labels:
    app: cluster-autoscaler
spec:
  replicas: 1
  selector:
    matchLabels:
      app: cluster-autoscaler
  template:
    metadata:
      labels:
        app: cluster-autoscaler
    spec:
      serviceAccountName: admin
      containers:
        - image: registry.cn-hangzhou.aliyuncs.com/google-containers/cluster-autoscaler:v1.1.0
          name: cluster-autoscaler
          resources:
            limits:
              cpu: 100m
              memory: 300Mi
            requests:
              cpu: 100m
              memory: 300Mi
          command:
            - ./cluster-autoscaler
            - --v=4
            - --stderrthreshold=info
            - --cloud-provider=alicloud
            - --skip-nodes-with-local-storage=false
            - --nodes=1:100:${AUTO_SCALER_GROUP}
          env:
          - name: ACCESS_KEY_ID
            valueFrom:
              secretKeyRef:
                name: cloud-config
                key: access-key-id
          - name: ACCESS_KEY_SECRET
            valueFrom:
              secretKeyRef:
                name: cloud-config
                key: access-key-secret
          imagePullPolicy: "Always"

// CloudProvider contains configuration info and functions for interacting with
// cloud provider (GCE, AWS, etc).
type CloudProvider interface {Marcin Wielgus, 3 years ago: • Cluster-autoscaler: cloud provider interface
	// Name returns name of the cloud provider.
	Name() string

	// NodeGroups returns all node groups configured for this cloud provider.
	//返回所有伸缩组
	NodeGroups() []NodeGroup

	// NodeGroupForNode returns the node group for the given node, nil if the node
	// should not be processed by cluster autoscaler, or non-nil error if such
	// occurred. Must be implemented.
	NodeGroupForNode(*apiv1.Node) (NodeGroup, error)

	// Pricing returns pricing model for this cloud provider or error if not available.
	// Implementation optional.
	Pricing() (PricingModel, errors.AutoscalerError)

	// GetAvailableMachineTypes get all machine types that can be requested from the cloud provider.
	// Implementation optional.
	GetAvailableMachineTypes() ([]string, error)

	// NewNodeGroup builds a theoretical node group based on the node definition provided. The node group is not automatically
	// created on the cloud provider side. The node group is not returned by NodeGroups() until it is created.
	// Implementation optional.
	NewNodeGroup(machineType string, labels map[string]string, systemLabels map[string]string,
		taints []apiv1.Taint, extraResources map[string]resource.Quantity) (NodeGroup, error)

	// GetResourceLimiter returns struct containing limits (max, min) for resources (cores, memory etc.).
	GetResourceLimiter() (*ResourceLimiter, error)

	// GPULabel returns the label added to nodes with GPU resource.
	GPULabel() string

	// GetAvailableGPUTypes return all available GPU types cloud provider supports.
	GetAvailableGPUTypes() map[string]struct{}

	// Cleanup cleans up open resources before the cloud provider is destroyed, i.e. go routines etc.
	Cleanup() error

	// Refresh is called before every main loop and can be used to dynamically update cloud provider state.
	// In particular the list of node groups returned by NodeGroups can change as a result of CloudProvider.Refresh().
	Refresh() error
}

// NodeGroup contains configuration info and functions to control a set
// of nodes that have the same capacity and set of labels.
type NodeGroup interface {
	// MaxSize returns maximum size of the node group.
	MaxSize() int

	// MinSize returns minimum size of the node group.
	MinSize() int

	// TargetSize returns the current target size of the node group. It is possible that the
	// number of nodes in Kubernetes is different at the moment but should be equal
	// to Size() once everything stabilizes (new nodes finish startup and registration or
	// removed nodes are deleted completely). Implementation required.
	TargetSize() (int, error)

	// IncreaseSize increases the size of the node group. To delete a node you need
	// to explicitly name it and use DeleteNode. This function should wait until
	// node group size is updated. Implementation required.
	//扩容伸缩组
	IncreaseSize(delta int) error

	// DeleteNodes deletes nodes from this node group. Error is returned either on
	// failure or if the given node doesn't belong to this node group. This function
	// should wait until node group size is updated. Implementation required.
	//从伸缩组中删除节点
	DeleteNodes([]*apiv1.Node) error

	// DecreaseTargetSize decreases the target size of the node group. This function
	// doesn't permit to delete any existing node and can be used only to reduce the
	// request for new nodes that have not been yet fulfilled. Delta should be negative.
	// It is assumed that cloud provider will not delete the existing nodes when there
	// is an option to just decrease the target. Implementation required.
	DecreaseTargetSize(delta int) error

	// Id returns an unique identifier of the node group.
	Id() string

	// Debug returns a string containing all information regarding this node group.
	Debug() string

	// Nodes returns a list of all nodes that belong to this node group.
	// It is required that Instance objects returned by this method have Id field set.
	// Other fields are optional.
	Nodes() ([]Instance, error)

	// TemplateNodeInfo returns a schedulernodeinfo.NodeInfo structure of an empty
	// (as if just started) node. This will be used in scale-up simulations to
	// predict what would a new node look like if a node group was expanded. The returned
	// NodeInfo is expected to have a fully populated Node object, with all of the labels,
	// capacity and allocatable information as well as all pods that are started on
	// the node by default, using manifest (most likely only kube-proxy). Implementation optional.
	TemplateNodeInfo() (*schedulernodeinfo.NodeInfo, error)

	// Exist checks if the node group really exists on the cloud provider side. Allows to tell the
	// theoretical node group from the real one. Implementation required.
	Exist() bool

	// Create creates the node group on the cloud provider side. Implementation optional.
	Create() (NodeGroup, error)

	// Delete deletes the node group on the cloud provider side.
	// This will be executed only for autoprovisioned node groups, once their size drops to 0.
	// Implementation optional.
	Delete() error

	// Autoprovisioned returns true if the node group is autoprovisioned. An autoprovisioned group
	// was created by CA and can be deleted when scaled to 0.
	Autoprovisioned() bool
}