Metrics Server 完整配置安装手册

Metrics Server 是 Kubernetes 集群的核心组件之一，用于聚合集群中节点和 Pod 的资源使用数据（如 CPU、内存），并通过 Metrics API 提供给 Horizontal Pod Autoscaler (HPA) 或 kubectl top 等工具使用。它轻量、高效，通常用于监控和自动扩缩容场景。本教程将教你如何完成Metrics Server 完整配置安装！

1. 删除现有部署（如有）

# 删除现有的 Metrics Server
kubectl delete -f https://github.com/kubernetes-sigs/metrics-server/releases/latest/download/components.yaml --ignore-not-found=true# 或者强制删除所有相关资源
kubectl delete deployment metrics-server -n kube-system --ignore-not-found=true
kubectl delete service metrics-server -n kube-system --ignore-not-found=true
kubectl delete apiservice v1beta1.metrics.k8s.io --ignore-not-found=true
kubectl delete clusterrole system:aggregated-metrics-reader --ignore-not-found=true
kubectl delete clusterrolebinding metrics-server:system:auth-delegator --ignore-not-found=true
kubectl delete rolebinding metrics-server-auth-reader -n kube-system --ignore-not-found=true
kubectl delete clusterrolebinding metrics-server:system:metrics-server --ignore-not-found=true

2. 创建完整配置文件

创建 metrics-server.yaml 文件：

cat > metrics-server-fixed.yaml << 'EOF'
apiVersion: v1
kind: ServiceAccount
metadata:labels:k8s-app: metrics-servername: metrics-servernamespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:labels:k8s-app: metrics-serverrbac.authorization.k8s.io/aggregate-to-admin: "true"rbac.authorization.k8s.io/aggregate-to-edit: "true"rbac.authorization.k8s.io/aggregate-to-view: "true"name: system:aggregated-metrics-reader
rules:
- apiGroups:- metrics.k8s.ioresources:- pods- nodesverbs:- get- list- watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:labels:k8s-app: metrics-servername: system:metrics-server
rules:
- apiGroups:- ""resources:- nodes/metricsverbs:- get
- apiGroups:- ""resources:- pods- nodesverbs:- get- list- watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:labels:k8s-app: metrics-servername: metrics-server-auth-readernamespace: kube-system
roleRef:apiGroup: rbac.authorization.k8s.iokind: Rolename: extension-apiserver-authentication-reader
subjects:
- kind: ServiceAccountname: metrics-servernamespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:labels:k8s-app: metrics-servername: metrics-server:system:auth-delegator
roleRef:apiGroup: rbac.authorization.k8s.iokind: ClusterRolename: system:auth-delegator
subjects:
- kind: ServiceAccountname: metrics-servernamespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:labels:k8s-app: metrics-servername: metrics-server:system:metrics-server
roleRef:apiGroup: rbac.authorization.k8s.iokind: ClusterRolename: system:metrics-server
subjects:
- kind: ServiceAccountname: metrics-servernamespace: kube-system
---
apiVersion: v1
kind: Service
metadata:labels:k8s-app: metrics-servername: metrics-servernamespace: kube-system
spec:ports:- name: httpsport: 443protocol: TCPtargetPort: httpsselector:k8s-app: metrics-server
---
apiVersion: apps/v1
kind: Deployment
metadata:labels:k8s-app: metrics-servername: metrics-servernamespace: kube-system
spec:selector:matchLabels:k8s-app: metrics-serverstrategy:rollingUpdate:maxUnavailable: 0template:metadata:labels:k8s-app: metrics-serverspec:containers:- args:- --cert-dir=/tmp- --secure-port=4443- --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname- --kubelet-use-node-status-port- --kubelet-insecure-tlsimage: registry.cn-hangzhou.aliyuncs.com/google_containers/metrics-server:v0.7.1imagePullPolicy: IfNotPresentlivenessProbe:failureThreshold: 3httpGet:path: /livezport: httpsscheme: HTTPSperiodSeconds: 10name: metrics-serverports:- containerPort: 4443name: httpsprotocol: TCPreadinessProbe:failureThreshold: 3httpGet:path: /readyzport: httpsscheme: HTTPSinitialDelaySeconds: 20periodSeconds: 10resources:requests:cpu: 100mmemory: 200MisecurityContext:allowPrivilegeEscalation: falsereadOnlyRootFilesystem: truerunAsNonRoot: truerunAsUser: 1000volumeMounts:- mountPath: /tmpname: tmp-dirnodeSelector:kubernetes.io/os: linuxpriorityClassName: system-cluster-criticalserviceAccountName: metrics-servervolumes:- emptyDir: {}name: tmp-dir
---
apiVersion: apiregistration.k8s.io/v1
kind: APIService
metadata:labels:k8s-app: metrics-servername: v1beta1.metrics.k8s.io
spec:group: metrics.k8s.iogroupPriorityMinimum: 100insecureSkipTLSVerify: trueservice:name: metrics-servernamespace: kube-systemversion: v1beta1versionPriority: 100
EOF

3. 应用配置

# 应用完整配置
kubectl apply -f metrics-server.yaml

4. 等待部署完成

# 等待 Pod 启动
kubectl wait --for=condition=ready pod -l k8s-app=metrics-server -n kube-system --timeout=180s# 或者实时观察部署状态
kubectl get pods -n kube-system -l k8s-app=metrics-server -w

5. 验证安装

# 检查 Pod 状态
kubectl get pods -n kube-system -l k8s-app=metrics-server# 测试 Metrics Server 功能
kubectl top nodes# 测试 Pod 指标
kubectl top pods -A# 检查 API 服务状态
kubectl get apiservice v1beta1.metrics.k8s.io

6. 故障排除

如果出现镜像拉取问题

选项一：使用国内镜像源

# 修改镜像地址
sed -i 's|k8s.gcr.io/metrics-server/metrics-server:v0.7.1|registry.cn-hangzhou.aliyuncs.com/google_containers/metrics-server:v0.7.1|g' metrics-server.yaml# 重新应用
kubectl apply -f metrics-server.yaml

选项二：使用官方最新版本

# 下载最新版本
curl -LO https://github.com/kubernetes-sigs/metrics-server/releases/latest/download/components.yaml# 应用
kubectl apply -f components.yaml

检查详细日志

# 查看 Pod 详细信息
kubectl describe pod -n kube-system -l k8s-app=metrics-server# 查看日志
kubectl logs -n kube-system -l k8s-app=metrics-server

重启部署

# 重启 Metrics Server
kubectl rollout restart deployment/metrics-server -n kube-system

7. 配置说明

这个完整配置包含以下关键特性：

• 安全配置：使用非 root 用户运行，只读根文件系统
• 资源限制：CPU 100m，内存 200Mi
• 健康检查：就绪性和存活探针
• TLS 配置：跳过 Kubelet TLS 验证（--kubelet-insecure-tls）
• 高可用：滚动更新策略
• 优先级：系统集群关键优先级

8. 验证 HPA 功能

安装完成后，可以测试 HPA：

# 创建测试部署
kubectl create deployment hpa-test --image=nginx:alpine# 创建 HPA
kubectl autoscale deployment hpa-test --cpu-percent=50 --min=1 --max=3# 观察 HPA
kubectl get hpa hpa-test -w

这个完整配置应该能够解决大多数 Metrics Server 的安装问题。