目录
现象
当需要查看资源的占用的时候执行以下命令， 提示缺少组件：
[root@master k8s-metric-server]# kubectl top pod
error: Metrics API not available
安装Metric-Server
版本关系
下载部署文件
参考 https://github.com/kubernetes-sigs/metrics-server
wget https://github.com/kubernetes-sigs/metrics-server/releases/latest/download/components.yaml -O metrics-server-components.yaml
若下载有问题可以直接复制下面内容 (以下为原始文件)
metrics-server-components.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
labels:
k8s-app: metrics-server
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
k8s-app: metrics-server
rbac.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.io
resources:
- pods
- nodes
verbs:
- get
- list
- watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
k8s-app: metrics-server
name: system:metrics-server
rules:
- apiGroups:
- ""
resources:
- nodes/metrics
verbs:
- get
- apiGroups:
- ""
resources:
- pods
- nodes
verbs:
- get
- list
- watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
labels:
k8s-app: metrics-server
name: metrics-server-auth-reader
namespace: kube-system
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: Role
name: extension-apiserver-authentication-reader
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
labels:
k8s-app: metrics-server
name: metrics-server:system:auth-delegator
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: system:auth-delegator
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
labels:
k8s-app: metrics-server
name: system:metrics-server
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: system:metrics-server
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
---
apiVersion: v1
kind: Service
metadata:
labels:
k8s-app: metrics-server
name: metrics-server
namespace: kube-system
spec:
ports:
- name: https
port: 443
protocol: TCP
targetPort: https
selector:
k8s-app: metrics-server
---
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
k8s-app: metrics-server
name: metrics-server
namespace: kube-system
spec:
selector:
matchLabels:
k8s-app: metrics-server
strategy:
rollingUpdate:
maxUnavailable: 0
template:
metadata:
labels:
k8s-app: metrics-server
spec:
containers:
- args:
- --cert-dir=/tmp
- --secure-port=10250
- --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname
- --kubelet-use-node-status-port
- --metric-resolution=15s
- --kubelet-insecure-tls
image: registry.k8s.io/metrics-server/metrics-server:v0.7.0
imagePullPolicy: IfNotPresent
livenessProbe:
failureThreshold: 3
httpGet:
path: /livez
port: https
scheme: HTTPS
periodSeconds: 10
name: metrics-server
ports:
- containerPort: 10250
name: https
protocol: TCP
readinessProbe:
failureThreshold: 3
httpGet:
path: /readyz
port: https
scheme: HTTPS
initialDelaySeconds: 20
periodSeconds: 10
resources:
requests:
cpu: 100m
memory: 200Mi
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
volumeMounts:
- mountPath: /tmp
name: tmp-dir
nodeSelector:
kubernetes.io/os: linux
priorityClassName: system-cluster-critical
serviceAccountName: metrics-server
volumes:
- emptyDir: {}
name: tmp-dir
---
apiVersion: apiregistration.k8s.io/v1
kind: APIService
metadata:
labels:
k8s-app: metrics-server
name: v1beta1.metrics.k8s.io
spec:
group: metrics.k8s.io
groupPriorityMinimum: 100
insecureSkipTLSVerify: true
service:
name: metrics-server
namespace: kube-system
version: v1beta1
versionPriority: 100
修改镜像地址
需要注意的是，metrics-server镜像用的是gcr镜像，需要换到国内的镜像仓库
将原始yaml文件中的
# 将 registry.k8s.io/metrics-server/metrics-server:v0.7.0
# 替换为以下镜像
registry.aliyuncs.com/google_containers/metrics-server:v0.7.0
修改TLS配置, 在原始metrics-server-components.yaml文件对应位置增加下面的参数, 具体原因在下面 问题一
......
containers:
- args:
...
- --kubelet-insecure-tls
......
部署
kubectl apply -f metrics-server-components.yaml
验证效果
# 执行以下命令可以成功返回pod的资源使用情况
[root@master k8s-metric-server]# kubectl top pod
NAME CPU(cores) MEMORY(bytes)
mysql-5d7f8bd64f-7kcnx 3m 661Mi
nfs-client-provisioner-867b699cb5-nvhmx 2m 8Mi
center-offline-5b66d879b8-79kk8 2m 827Mi
a-offline-5f68f9489-jl7lt 5m 950Mi
b-offline-5f68f9489-xkc7p 3m 1034Mi
问题一
Apply 之后查看pod状态, pod开始running, 但是一直不ready
[root@master k8s-metric-server]# kubectl get pods -n kube-system | grep metrics
metrics-server-7587785854-t8dpl 0/1 Running 0 5m28s
原因
官方文档中, 如下红框中说明，Kubelet证书需要由群集证书颁发机构签名（或可以禁用证书验证，通过对Metrics Server配置参数–Kubelet-insecure-tls不安全）
解决办法
如下红框中说明，添加了“–Kubelet-insecure-tls”这个配置，就不会去验证Kubelets提供的服务证书的CA
我们对应修改原始yaml文件, 增加参数
......
containers:
- args:
...
- --kubelet-insecure-tls
......
修改之后重新执行
kubectl apply -f metrics-server-components.yaml
重新查看状态, 可以发现已经ready
[root@master k8s-metric-server]# kubectl get pods -n kube-system | grep metrics
metrics-server-5cc466bcdc-vbjjb 1/1 Running 0 62s