k8s部署Prometheus+Grafana

1.prometheus简介

Prometheus是一个开源的系统监控和警报工具包，最初由SoundCloud开发的，社区活跃，2016年加入了云原生计算基金会成为继Kubernetes之后的第二个托管项目；普罗米修斯以时间序列数据的形式收集并存储度量值；大部分模块由Go语言编写的。

Prometheus架构图

2.部署Prometheus

1)部署Prometheus deploy

cat prome_deploy.yml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus
  namespace: work
  labels:
    app: prometheus
spec:
  selector:
    matchLabels:
      app: prometheus
  template:
    metadata:
      labels:
        app: prometheus
    spec:
      securityContext:                                   #指定运行的用户为root
        runAsUser: 0
      serviceAccountName: prometheus
      containers:
      - image: prom/prometheus:v2.30.2
        name: prometheus
        args:
        - "--config.file=/etc/prometheus/prometheus.yml" #通过volume挂载prometheus.yml
        - "--storage.tsdb.path=/prometheus"              #通过vlolume挂载目录/prometheus
        - "--storage.tsdb.retention.time=24h"
        - "--web.enable-admin-api"                       #控制对admin HTTP API的访问
        - "--web.enable-lifecycle"                       #支持热更新，直接执行localhost:9090/-/reload立即生效
        ports:
        - containerPort: 9090
          name: http
        volumeMounts:
        - mountPath: "/etc/prometheus"
          name: config-volume
        - mountPath: "/prometheus"
          name: data
        resources:
          requests:
            cpu: 100m
            memory: 512Mi
          limits:
            cpu: 100m
            memory: 512Mi
      volumes:
      - name: data
        persistentVolumeClaim:
          claimName: prometheus-data  #本地存储
      - name: config-volume
        configMap:
          name: prometheus-config     #定义的prometeus.yaml

kubectl apply -f prome_deploy.yml

2)部署Prometheus service

cat prome_svc.yml

apiVersion: v1
kind: Service
metadata:
  name: prometheus
  namespace: work
  labels:
    app: prometheus
spec:
  selector:
    app: prometheus
  type: NodePort
  ports:
    - name: web
      port: 9090
      targetPort: http

kubectl apply -f prome_svc.yml

3)部署configmap

cat pome_cfg.yml

apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-config
  namespace: work
data:
  prometheus.yml: |
    global:
      scrape_interval: 15s
      scrape_timeout: 15s
    scrape_configs:
    - job_name: 'prometheus'
      static_configs:
      - targets: ['localhost:9090']

 kubectl apply -f prome_cfg.yml

4)部署PV，PVC

apiVersion: v1
kind: PersistentVolume
metadata:
  name: prometheus-local
  labels:
    app: prometheus
spec:
  accessModes:
  - ReadWriteOnce
  capacity:
    storage: 5Gi
  storageClassName: local-storage
  local:
    path: /data/k8s/prometheus  #在k8s节点创建此目录
  nodeAffinity:
    required:
      nodeSelectorTerms:
      - matchExpressions:
        - key: kubernetes.io/hostname
          operator: In
          values:
          - node   #指定运行在node节点
  persistentVolumeReclaimPolicy: Retain
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: prometheus-data
  namespace: work
spec:
  selector:
    matchLabels:
      app: prometheus
  accessModes:
  - ReadWriteOnce
  resources:
    requests:
      storage: 5Gi
  storageClassName: local-storage

kubectl apply -f prome_pvc.yml

5)配置rabc

apiVersion: v1
kind: ServiceAccount	#创建一个serviceaccount
metadata:
  name: prometheus
 namespace: work

apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole	创建一个clusterrole
metadata:
  name: prometheus
rules:
- apiGroups:
  - ""
  resources:
  - nodes
  - services
  - endpoints
  - pods
  - nodes/proxy
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - "extensions"
  resources:
    - ingresses
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - ""
  resources:
  - configmaps
  - nodes/metrics
  verbs:
  - get
- nonResourceURLs:
  - /metrics
  verbs:
  - get
---
apiVersion: rbac.authorization.k8s.io/v1beta1
kind: ClusterRoleBinding
metadata:
  name: prometheus
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: prometheus
subjects:
- kind: ServiceAccount
  name: prometheus
  namespace: work

kubectl apply -f prome_rabc.yml

查看部署的Prometheus服务

[root@master ~]# kubectl get pod,svc,configmap,sa -n work
NAME                              READY   STATUS    RESTARTS   AGE
pod/prometheus-5f58d57f4c-fflv7   1/1     Running   3          3d20h

NAME                 TYPE       CLUSTER-IP      EXTERNAL-IP   PORT(S)          AGE
service/prometheus   NodePort   10.100.21.177   <none>        9090:32075/TCP   3d20h

NAME                          DATA   AGE
configmap/prometheus-config   1      3d20h

NAME                        SECRETS   AGE
serviceaccount/default      1         3d20h
serviceaccount/prometheus   1         3d20h

在浏览器访问Prometheus
访问地址是node节点IP加上service的nodeport端口

3.部署grafana

1)部署deployment

cat grafana.yml

kind: Deployment
apiVersion: apps/v1
metadata:
  labels:
    app: grafana
  name: grafana
  namespace: work
spec:
  replicas: 1
  revisionHistoryLimit: 10
  selector:
    matchLabels:
      app: grafana
  template:
    metadata:
      labels:
        app: grafana
    spec:
      securityContext:
        runAsNonRoot: true
        runAsUser: 10555
        fsGroup: 10555
      containers:
        - name: grafana
          image: grafana/grafana:8.4.4
          imagePullPolicy: IfNotPresent
          env:
            - name: GF_AUTH_BASIC_ENABLED
              value: "true"
            - name: GF_AUTH_ANONYMOUS_ENABLED
              value: "false"
          readinessProbe:
            httpGet:
              path: /login
              port: 3000
          volumeMounts:
            - mountPath: /var/lib/grafana
              name: grafana-data-volume
          ports:
            - containerPort: 3000
              protocol: TCP
      volumes:
        - name: grafana-data-volume
          emptyDir: {}

kubectl apply -f grafana.yml

2)部署svc

cat grafana_svc.yml

kind: Service
apiVersion: v1
metadata:
  labels:
    app: grafana
  name: grafana-service
  namespace: work
spec:
  ports:
    - port: 3000
      targetPort: 3000
  selector:
    app: grafana
  type: NodePort

kubectl apply -f grafana_svc.yml

查看部署的grafana服务

[root@master prometheus]# kubectl get pod,svc -n work |grep grafana
pod/grafana-5b86ddbbff-sq5nx      1/1     Running   0          5m33s
service/grafana-service   NodePort   10.107.134.50   <none>        3000:30362/TCP   5m25s

访问grafana
grafana访问地址为pod所在node节点IP+nodeport的端口

首次登录grafana，用户名和密码都是admin，登陆之后会要求修改admin的密码