k8s部署prometheus+grafana

crictl pull registry.cn-hangzhou.aliyuncs.com/google_containers/prometheus:latest

crictl pull docker.io/library/busybox:stable-glibc

crictl pull docker.io/grafana/grafana:latest

 

cat /data/prometheus-grafana/prometheus/prometheus-configmap.yaml

apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-config
  namespace: monitor
data:
  prometheus.yml: |
    global:
      scrape_interval: 15s
      evaluation_interval: 15s
    scrape_configs:
    - job_name: 'prometheus'
      static_configs:
      - targets: ['localhost:9090']
    - job_name: 'coredns'#coredns监控项
      static_configs:
      - targets: ['10.96.0.10:9153']
    - job_name: 'kube-apiserver'#添加kube-apiserver监控项
      scheme: https
      tls_config:
        insecure_skip_verify: true
        ca_file: '/var/run/secrets/kubernetes.io/serviceaccount/ca.crt'
      bearer_token_file: '/var/run/secrets/kubernetes.io/serviceaccount/token'
      static_configs:
      - targets: ['10.96.0.1:443']

    - job_name: 'cadvisor'
      kubernetes_sd_configs:
        - role: node
      scheme: https
      tls_config:
        insecure_skip_verify: true
        ca_file: '/var/run/secrets/kubernetes.io/serviceaccount/ca.crt'
      bearer_token_file: '/var/run/secrets/kubernetes.io/serviceaccount/token'
      relabel_configs:
      - target_label: __metrics_path__
        replacement: /metrics/cadvisor
    - job_name: "node_exporter"
      static_configs:
        - targets: ["service-8336.work.svc.cluster.local"]
          labels:
            instance: TradeWebTest

　　

cat /data/prometheus-grafana/prometheus/prometheus.yaml

#创建SA
apiVersion: v1
kind: ServiceAccount
metadata:
  name: prometheus
  namespace: monitor
 
---
#创建clusterrole
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: prometheus
rules:
- apiGroups:
  - ""
  resources:
  - nodes
  - services
  - endpoints
  - pods
  - nodes/proxy
  - nodes/proxy
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - "extenstions"
  resources:
    - ingresses
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - ""
  resources:
  - configmaps
  - nodes/metrics
  verbs:
  - get
- nonResourceURLs:
  - /metrics
  verbs:
  - get
 
---
#创建clusterrolebinding
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: prometheus
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: prometheus
subjects:
- kind: ServiceAccount
  name: prometheus
  namespace: monitor
 
---
#创建svc
apiVersion: v1
kind: Service
metadata:
  name: prometheus-svc
  namespace: monitor
  labels:
    app: prometheus
spec:
  selector:
    app: prometheus
  type: NodePort
  ports:
    - name: web
      nodePort: 32224
      port: 9090
      targetPort: http
 
---
#创建ingress
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
  name: prometheus-ingress
  namespace: monitor
spec:
  ingressClassName: nginx
  rules:
  - host: www.myprometheus.com
    http:
      paths:
      - path: /
        pathType: Prefix
        backend:
          service:
            name:  prometheus-svc
            port:
              number: 9090
---
#创建deployment
apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus
  namespace: monitor
  labels:
    app: prometheus
spec:
  selector:
    matchLabels:
      app: prometheus
  replicas: 1
  template:
    metadata:
      labels:
        app: prometheus
    spec:
      serviceAccountName: prometheus
      initContainers:
      - name: "change-permission-of-directory"
        image: docker.io/library/busybox:stable-glibc
        command: ["/bin/sh"]
        args: ["-c","chown -R 65534:65534 /prometheus"]
        securityContext:
          privileged: true
        volumeMounts:
        - mountPath: "/etc/prometheus"
          name: config-volume
        - mountPath: "/prometheus"
          name: data
      containers:
      - image: registry.cn-hangzhou.aliyuncs.com/google_containers/prometheus:latest
        name: prometheus
        args:
        - "--config.file=/etc/prometheus/prometheus.yml"#指定prometheus配置文件路径
        - "--storage.tsdb.path=/prometheus"#指定tsdb数据库存储路径
        - "--web.enable-lifecycle"#允许热更新，curl localhost:9090/-/reload 进行热更新
        - "--web.console.libraries=/usr/share/prometheus/console_libraries"
        - "--web.console.templates=/usr/share/prometheus/consoles"
        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
        hostPath:
          path: /data/prometheus-grafana/prometheus
      - configMap:
          name: prometheus-config
        name: config-volume
#---
##创建configmap
#apiVersion: v1
#kind: ConfigMap
#metadata:
#  name: prometheus-config
#  namespace: monitor
#data:
#  prometheus.yml: |
#    global:
#      scrape_interval: 15s
#      evaluation_interval: 15s
#    scrape_configs:
#    - job_name: 'prometheus'
#      static_configs:
#      - targets: ['localhost:9090']

　　

 

cat /data/prometheus-grafana/grafana/grafana-configMap.yaml

apiVersion: v1
kind: ConfigMap
metadata:
  name: grafana-config
  namespace: monitor
data:
  datasources.yaml: |-
    apiVersion: 1
    datasources:
    - name: Prometheus
      type: prometheus
      #url: http://prometheus-server.default.svc:9090
      url: http://prometheus-svc.monitor.svc.cluster.local:9090
      access: proxy
      isDefault: true

　　

cat /data/prometheus-grafana/grafana/grafana-deployment.yaml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: grafana-deployment
  namespace: monitor
spec:
  replicas: 1
  selector:
    matchLabels:
      app: grafana
  template:
    metadata:
      labels:
        app: grafana
    spec:
      containers:
      - name: grafana
        #image: grafana/grafana:latest
        image: docker.io/grafana/grafana:latest
        imagePullPolicy: Never
        ports:
        - containerPort: 3000
        volumeMounts:
        - name: grafana-config-volume
          mountPath: /etc/grafana/provisioning/datasources
      volumes:
      - name: grafana-config-volume
        configMap:
          name: grafana-config

---
apiVersion: v1
kind: Service
metadata:
  name: grafana-service
  namespace: monitor
spec:
  selector:
    app: grafana
  type: NodePort # 或者 LoadBalancer 如果你在云环境上运行，例如 GKE, EKS, AKS 等。
  ports:
  - port: 3000
    targetPort: 3000
    nodePort: 3000 # NodePort 的可选配置，只在 type 为 NodePort 时需要。