1.创建pv、pvc

apiVersion: v1
kind: PersistentVolume
metadata:
  name: prometheus
spec:
  capacity:
    storage: 10Gi
  accessModes:
  - ReadWriteOnce
  persistentVolumeReclaimPolicy: Retain
  nfs:
    server: 10.0.0.10
    path: /nfsdata/
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: prometheus
  namespace: kube-ops
spec:
  accessModes:
  - ReadWriteOnce
  resources:
    requests:
      storage: 10Gi

2.配置rbac

apiVersion: v1
kind: ServiceAccount
metadata:
  name: prometheus
  namespace: kube-ops

---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: prometheus
rules:
- apiGroups:
  - ""
  resources:
  - nodes
  - services
  - endpoints
  - pods
  - nodes/proxy
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - ""
  resources:
  - configmaps
  - nodes/metrics
  verbs:
  - get
- nonResourceURLs:
  - /metrics
  verbs:
  - get

---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: prometheus
roleRef:
  apiGroup: ""
  kind: ClusterRole
  name: prometheus
subjects:
  - kind: ServiceAccount
    name: prometheus
    namespace: kube-ops

3.创建service

apiVersion: v1
kind: Service
metadata:
  name: prometheus
  namespace: kube-ops
  annotations:
    prometheus.io/scrape: "true"
    prometheus.io/port: "9090"
spec:
  selector:
    app: prometheus
  type: NodePort
  ports:
    - name: http
      port: 9090
      targetPort: http
      nodePort: 30002

4.创建configmap

apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-conf
  namespace: kube-ops
data:
  rules.yml: |
    groups:
    - name: 系统硬件告警
      rules:
      - alert: NodeFilesystemUsage
        expr: (node_filesystem_size_bytes{mountpoint="/rootfs"} -  node_filesystem_free_bytes{mountpoint="/rootfs"} ) / node_filesystem_size_bytes{mountpoint="/rootfs"} * 100 > 80
        for: 10s
        labels:
          filesystem: node
        annotations:
          summary: "{{ $labels.instance }}:磁盘使用量"
          description: "{{ $labels.instance }}: rootfs使用{{ $value }},大于总容量的80%"
      - alert: NodeMemoryUsage
        expr: (node_memory_MemTotal_bytes - (node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes)) / node_memory_MemTotal_bytes * 100 > 90
        for: 10s
        labels:
          team: node
        annotations: 
          summary: "{{ $labels.instance }}: node节点内存使用过高"
          description: "{{ $labels.instance }}: 内存使用大于90%，当前已用{{ $value }}%"
  prometheus.yml: |
    global:
      scrape_interval:     15s
      evaluation_interval: 15s
    alerting:
      alertmanagers:
      - static_configs:
        - targets: ["alertmanager:9093"]
    rule_files:
    - "/etc/prometheus/rules.yml"
      # - "second.rules"

    scrape_configs:
      - job_name: prometheus
        static_configs:
        - targets: ['localhost:9090']
      - job_name: node_exporter
        kubernetes_sd_configs:
        - role: node
        relabel_configs:
        - source_labels: [__address__]
          regex: "(.*):10250"
          target_label: __address__
          replacement: "${1}:9100"
        - action: labelmap
          regex: "__meta_kubernetes_node_label_(.*)"
      - job_name: 'kubernetes-kubelet'
        scheme: https
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
          insecure_skip_verify: true
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        kubernetes_sd_configs:
        - role: node
        relabel_configs:
        - action: labelmap
          regex: __meta_kubernetes_node_label_(.+)
      - job_name: 'kubernetes-cadvisor'
        kubernetes_sd_configs:
        - role: node
        scheme: https
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
          insecure_skip_verify: true
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        relabel_configs:
        - action: labelmap
          regex: __meta_kubernetes_node_label_(.+)
        - action: replace
          source_labels: [__meta_kubernetes_node_name]
          regex: (.*)
          target_label: __metrics_path__
          replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
        - action: replace
          source_labels: [__address__]
          target_label: __address__
          replacement: kubernetes.default.svc:443
      - job_name: 'kubernetes-api-services'
        scheme: https
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        kubernetes_sd_configs:
        - role: endpoints
        relabel_configs:
        - action: replace
          source_labels: [__address__]
          target_label: __address__
          replacement: kubernetes.default:443
        - action: keep
          source_labels: [__meta_kubernetes_namespace,__meta_kubernetes_endpoint_port_name,__meta_kubernetes_service_name]
          regex: default;https;kubernetes
        - action: labelmap
          regex: __meta_kubernetes_(.+)
      - job_name: 'kubernetes-service-endpoints'
        kubernetes_sd_configs:
        - role: endpoints
        relabel_configs:
        - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
          action: keep
          regex: true
        # 将label标签中的端口替换为annotations中指定的端口
        - action: replace
          source_labels: [__address__,__meta_kubernetes_service_annotation_prometheus_io_port]
          target_label: __address__
          regex: (.*?):(\d+);(\d+)
          replacement: ${1}:${3}
        # 动态获取scheme，确保http和https都可以进行采集
        - action: replace
          source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
          target_label: __scheme__
          regex: (https?)
        - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
          action: replace
          target_label: __metrics_path__
          regex: (.+)
        - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
          action: replace
          target_label: __address__
          regex: ([^:]+)(?::\d+)?;(\d+)
          replacement: $1:$2
        - action: labelmap
          regex: __meta_kubernetes_service_label_(.+)
        - source_labels: [__meta_kubernetes_namespace]
          action: replace
          target_label: kubernetes_namespace
        - source_labels: [__meta_kubernetes_service_name]
          action: replace
          target_label: kubernetes_name

5.部署node_exporter

apiVersion: extensions/v1beta1
kind: DaemonSet
metadata:
  name: node-exporter
  namespace: kube-ops
  labels:
    name: node-exporter
spec:
  template:
    metadata:
      labels:
        name: node-exporter
    spec:
      hostPID: true
      hostIPC: true
      hostNetwork: true
      containers:
      - name: node-exporter
        image: prom/node-exporter:v0.16.0
        ports:
        - containerPort: 9100
        resources:
          requests:
            cpu: 0.15
        securityContext:
          privileged: true
        args:
        - --path.procfs
        - /host/proc
        - --path.sysfs
        - /host/sys
        - --collector.filesystem.ignored-mount-points
        - '"^/(sys|proc|dev|host|etc)($|/)"'
        volumeMounts:
        - name: dev
          mountPath: /host/dev
        - name: proc
          mountPath: /host/proc
        - name: sys
          mountPath: /host/sys
        - name: rootfs
          mountPath: /rootfs
      tolerations:
      - key: "node-role.kubernetes.io/master"
        operator: "Exists"
        effect: "NoSchedule"
      volumes:
        - name: proc
          hostPath:
            path: /proc
        - name: dev
          hostPath:
            path: /dev
        - name: sys
          hostPath:
            path: /sys
        - name: rootfs
          hostPath:
            path: /

6.部署prometheus deployment

apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  name: prometheus
  namespace: kube-ops
  labels:
    app: prometheus
spec:
  selector:
    matchLabels:
      app: prometheus
  template:
    metadata:
      labels:
        app: prometheus
    spec:
      serviceAccountName: prometheus
      containers:
      - name: prometheus
        image: prom/prometheus:v2.15.2
        command:
        - "/bin/prometheus"
        args:
        - "--config.file=/etc/prometheus/prometheus.yml"
        - "--storage.tsdb.path=/prometheus"
        - "--storage.tsdb.retention=7d"
        - "--web.enable-admin-api"
        - "--web.enable-lifecycle"
        ports:
        - name: http
          containerPort: 9090
          protocol: TCP
        volumeMounts:
        - name: config
          mountPath: "/etc/prometheus"
        - name: data
          subPath: prometheus
          mountPath: "/prometheus"
        resources:
          requests:
            cpu: 0.05
            memory: 512Mi
          limits:
            cpu: 1
            memory: 2Gi
      volumes:
      - name: config
        configMap:
          name: prometheus-conf
      - name: data
        persistentVolumeClaim:
          claimName: prometheus

最后更新于 2020-08-26 02:57:47 并被添加「k8s prometheus」标签，已有 186 位童鞋阅读过。

本站使用「署名 4.0 国际」创作共享协议，可自由转载、引用，但需署名作者且注明文章出处

相关文章

• Traefik配置Let's Encrypt自动生成证书[alidns](三)
• prometheus监控kubernetes集群配置详解(七)
• alertmanager配置企业微信告警(六)
• alertmanager-webhook发送告警&恢复信息的请求体
• alertmanager自定义告警模板(五)