kubernetes监控-Heapster+InfluxDB+Grafana（十五）

cAdvisor+InfluxDB+Grafana

cAdvisor:是谷歌开源的一个容器监控工具，采集主机上容器相关的性能指标数据。比如CPU、内存、网络、文件系统等。

Heapster是谷歌开源的集群监控数据收集工具，会所有节点监控数据，Heapster作为一个pod在集群中运行，通过API获得集群中的所有节点，然后从节点kubelet暴露的10255汇总数据。目前社区用Metrics Server 取代 Heapster。

InfluxDB：时序数据库，存储监控数据。

Grafana：可视化展示。Grafana提供一个易于配置的仪表盘UI，可以轻松定制和扩展。

不足

l  功能单一，无法做到对K8S资源对象监控

l  告警单一，利用Grafana基本告警

l  依赖Influxdb，而Influxdb单点（高可用商业才支持），缺少开源精神

l  heapster在1.8+弃用，metrics-server取代

部署heapster组件

[root@localhost monitor]# cat heapster.yaml 
apiVersion: v1
kind: ServiceAccount
metadata:
  name: heapster
  namespace: kube-system

---

kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1beta1
metadata:
  name: heapster
roleRef:
  kind: ClusterRole
  name: cluster-admin
  apiGroup: rbac.authorization.k8s.io
subjects:
  - kind: ServiceAccount
    name: heapster
    namespace: kube-system

---

apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  name: heapster
  namespace: kube-system
spec:
  replicas: 1
  template:
    metadata:
      labels:
        task: monitoring
        k8s-app: heapster
    spec:
      serviceAccountName: heapster
      containers:
      - name: heapster
        image: registry.cn-hangzhou.aliyuncs.com/google-containers/heapster-amd64:v1.5.1
        imagePullPolicy: IfNotPresent
        command:
        - /heapster
        - --source=kubernetes:https://kubernetes.default
        - --sink=influxdb:http://monitoring-influxdb:8086

---

apiVersion: v1
kind: Service
metadata:
  labels:
    task: monitoring
    kubernetes.io/cluster-service: 'true'
    kubernetes.io/name: Heapster
  name: heapster
  namespace: kube-system
spec:
  ports:
  - port: 80
    targetPort: 8082
  selector:
    k8s-app: heapster

使用top命令

[root@localhost monitor]# kubectl top nodes
NAME            CPU(cores)   CPU%   MEMORY(bytes)   MEMORY%
192.168.0.220   208m         %    1978Mi          %
192.168.0.221   137m         %     1068Mi          %
192.168.0.222   135m         %     1009Mi          %
[root@localhost monitor]# kubectl top pods
NAME                     CPU(cores)   MEMORY(bytes)
nginx-7db9fccd9b-qkb7t   0m           2Mi
nginx-7db9fccd9b-wtvk8   0m           3Mi
nginx-7db9fccd9b-xxkzb   0m           2Mi

登录Dashboard即可查看到对应的监控图表

部署grafana和influxdb

[root@localhost monitor]# cat grafana.yaml
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  name: monitoring-grafana
  namespace: kube-system
spec:
  replicas:
  template:
    metadata:
      labels:
        task: monitoring
        k8s-app: grafana
    spec:
      containers:
      - name: grafana
        image: registry.cn-hangzhou.aliyuncs.com/google-containers/heapster-grafana-amd64:v4.4.1
        ports:
          - containerPort:
            protocol: TCP
        volumeMounts:
        - mountPath: /var
          name: grafana-storage
        env:
        - name: INFLUXDB_HOST
          value: monitoring-influxdb
        - name: GF_AUTH_BASIC_ENABLED
          value: "false"
        - name: GF_AUTH_ANONYMOUS_ENABLED
          value: "true"
        - name: GF_AUTH_ANONYMOUS_ORG_ROLE
          value: Admin
        - name: GF_SERVER_ROOT_URL
          value: /
      volumes:
      - name: grafana-storage
        emptyDir: {}

---

apiVersion: v1
kind: Service
metadata:
  labels:
    kubernetes.io/cluster-service: 'true'
    kubernetes.io/name: monitoring-grafana
  name: monitoring-grafana
  namespace: kube-system
spec:
  type: NodePort
  ports:
  - port :
    targetPort:
  selector:
    k8s-app: grafana

[root@localhost monitor]# cat influxdb.yaml
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  name: monitoring-influxdb
  namespace: kube-system
spec:
  replicas:
  template:
    metadata:
      labels:
        task: monitoring
        k8s-app: influxdb
    spec:
      containers:
      - name: influxdb
        image: registry.cn-hangzhou.aliyuncs.com/google-containers/heapster-influxdb-amd64:v1.1.1
        volumeMounts:
        - mountPath: /data
          name: influxdb-storage
      volumes:
      - name: influxdb-storage
        emptyDir: {}

---

apiVersion: v1
kind: Service
metadata:
  labels:
    task: monitoring
    kubernetes.io/cluster-service: 'true'
    kubernetes.io/name: monitoring-influxdb
  name: monitoring-influxdb
  namespace: kube-system
spec:
  ports:
  - port:
    targetPort:
  selector:
    k8s-app: influxdb

[root@localhost monitor]# kubectl apply -f .
deployment.extensions/monitoring-grafana unchanged
service/monitoring-grafana unchanged
serviceaccount/heapster unchanged
clusterrolebinding.rbac.authorization.k8s.io/heapster unchanged
deployment.extensions/heapster unchanged
service/heapster unchanged
deployment.extensions/monitoring-influxdb unchanged
service/monitoring-influxdb unchanged

查看

[root@localhost monitor]# kubectl get pod,svc,deploy -n kube-system -o wide
NAME                                        READY   STATUS    RESTARTS   AGE     IP             NODE            NOMINATED NODE   READINESS GATES
pod/coredns-5b8c57999b-z9jh8                /     Running             22h     172.17.52.3    192.168.0.220   <none>           <none>
pod/heapster-77f96f6f6c-qcr98               /     Running             14m     172.17.52.2    192.168.0.220   <none>           <none>
pod/kubernetes-dashboard-644c96f9c6-bvw8w   /     Running             23h     172.17.100.2   192.168.0.222   <none>           <none>
pod/monitoring-grafana--cb86b     /     Running             8m55s   172.17.100.5   192.168.0.222   <none>           <none>
pod/monitoring-influxdb-58b849b9f8-t26p8    /     Running             8m52s   172.17.50.4    192.168.0.221   <none>           <none>

NAME                           TYPE        CLUSTER-IP   EXTERNAL-IP   PORT(S)         AGE   SELECTOR
service/heapster               ClusterIP   10.0.0.208   <none>        /TCP          14m   k8s-app=heapster
service/kube-dns               ClusterIP   10.0.0.2     <none>        /UDP,/TCP   23h   k8s-app=kube-dns
service/kubernetes-dashboard   NodePort    10.0.0.84    <none>        :/TCP   23h   k8s-app=kubernetes-dashboard
service/monitoring-grafana     NodePort    10.0.0.252   <none>        :/TCP    14m   k8s-app=grafana
service/monitoring-influxdb    ClusterIP   10.0.0.85    <none>        /TCP        14m   k8s-app=influxdb

访问grafana：http://192.168.0.222:35811

导入图表