Kubernetes部署alertmanager

应用 alertmanager-configmap.yaml

apiVersion: v1
kind: ConfigMap
metadata:
  name: alertmanager-config
  namespace: kube-system
  labels:
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: EnsureExists
data:
  alertmanager.yml: |
    global:
      resolve_timeout: 5m
      smtp_smarthost: 'smtp.qq.com:463'
      smtp_from: '1335402049@qq.com'
      smtp_auth_username: '1335402049@qq.com'
      smtp_auth_password: 'xxxxxxxxx'

    receivers:
    - name: default-receiver
      email_configs:
      - to: "1335402049@qq.com"

    route:
      group_interval: 1m
      group_wait: 10s
      receiver: default-receiver
      repeat_interval: 1m

应用 alertmanager-pvc.yaml

apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: alertmanager
  namespace: kube-system
  labels:
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: EnsureExists
spec:
  storageClassName: managed-nfs-storage
  accessModes:
    - ReadWriteOnce
  resources:
    requests:
      storage: "1Gi"

应用 alertmanager-deployment.yaml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: alertmanager
  namespace: kube-system
  labels:
    k8s-app: alertmanager
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
    version: v0.14.0
spec:
  replicas: 1
  selector:
    matchLabels:
      k8s-app: alertmanager
      version: v0.14.0
  template:
    metadata:
      labels:
        k8s-app: alertmanager
        version: v0.14.0
      annotations:
        scheduler.alpha.kubernetes.io/critical-pod: ''
    spec:
      priorityClassName: system-cluster-critical
      containers:
        - name: prometheus-alertmanager
          image: "prom/alertmanager:v0.14.0"
          imagePullPolicy: "IfNotPresent"
          args:
            - --config.file=/etc/config/alertmanager.yml
            - --storage.path=/data
            - --web.external-url=/
          ports:
            - containerPort: 9093
          readinessProbe:
            httpGet:
              path: /#/status
              port: 9093
            initialDelaySeconds: 30
            timeoutSeconds: 30
          volumeMounts:
            - name: config-volume
              mountPath: /etc/config
            - name: storage-volume
              mountPath: "/data"
              subPath: ""
          resources:
            limits:
              cpu: 10m
              memory: 50Mi
            requests:
              cpu: 10m
              memory: 50Mi
        - name: prometheus-alertmanager-configmap-reload
          image: "jimmidyson/configmap-reload:v0.1"
          imagePullPolicy: "IfNotPresent"
          args:
            - --volume-dir=/etc/config
            - --webhook-url=http://localhost:9093/-/reload
          volumeMounts:
            - name: config-volume
              mountPath: /etc/config
              readOnly: true
          resources:
            limits:
              cpu: 10m
              memory: 10Mi
            requests:
              cpu: 10m
               memory: 10Mi
      volumes:
        - name: config-volume
          configMap:
            name: alertmanager-config
        - name: storage-volume
          persistentVolumeClaim:
            claimName: alertmanager

应用 alertmanager-service.yaml

apiVersion: v1
kind: Service
metadata:
  name: alertmanager
  namespace: kube-system
  labels:
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
    kubernetes.io/name: "Alertmanager"
spec:
  ports:
    - name: http
      port: 80
      protocol: TCP
      targetPort: 9093
  selector:
    k8s-app: alertmanager
  type: "ClusterIP"

修改prometheus-configmap.yaml

# 修改alert相关配置
alerting:
      # 告警配置文件
      alertmanagers:
      - static_configs:
          - targets: ["alertmanager:80"]

修改prometheus-configmap.yaml

# 增加rule_files配置
data:
  prometheus.yml: |
    # 添加：指定读取rules配置
    rule_files:
    - /etc/config/rules/*.rules

重新应用

kubectl apply -f prometheus-configmap.yaml

编写prometheus-rules.yaml并应用

apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-rules
  namespace: kube-system
data:
  # 通用角色
  general.rules: |
    groups:
    - name: general.rules
      rules:
      - alert: InstanceDown
        expr: up == 0
        for: 1m
        labels:
          severity: error 
        annotations:
          summary: "Instance {{ $labels.instance }} 停止工作"
          description: "{{ $labels.instance }} job {{ $labels.job }} 已经停止5分钟以上."
  # Node对所有资源的监控
  node.rules: |
    groups:
    - name: node.rules
      rules:
      - alert: NodeFilesystemUsage
        expr: 100 - (node_filesystem_free_bytes{fstype=~"ext4|xfs"} / node_filesystem_size_bytes{fstype=~"ext4|xfs"} * 100) > 80 
        for: 1m
        labels:
          severity: warning 
        annotations:
          summary: "Instance {{ $labels.instance }} : {{ $labels.mountpoint }} 分区使用率过高"
          description: "{{ $labels.instance }}: {{ $labels.mountpoint }} 分区使用大于80% (当前值: {{ $value }})"

      - alert: NodeMemoryUsage
        expr: 100 - (node_memory_MemFree_bytes+node_memory_Cached_bytes+node_memory_Buffers_bytes) / node_memory_MemTotal_bytes * 100 > 80
        for: 1m
        labels:
          severity: warning
        annotations:
          summary: "Instance {{ $labels.instance }} 内存使用率过高"
          description: "{{ $labels.instance }}内存使用大于80% (当前值: {{ $value }})"

      - alert: NodeCPUUsage    
        expr: 100 - (avg(irate(node_cpu_seconds_total{mode="idle"}[5m])) by (instance) * 100) > 60 
        for: 1m
        labels:
          severity: warning
        annotations:
          summary: "Instance {{ $labels.instance }} CPU使用率过高"       
          description: "{{ $labels.instance }}CPU使用大于60% (当前值: {{ $value }})"

挂载rules到prometheus-statefulset

apiVersion: apps/v1
kind: StatefulSet
metadata:
  name: prometheus
  # 部署命名空间 
  namespace: kube-system
  labels:
    k8s-app: prometheus
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
    version: v2.2.1
spec:
  serviceName: "prometheus"
  replicas: 1
  podManagementPolicy: "Parallel"
  updateStrategy:
   type: "RollingUpdate"
  selector:
    matchLabels:
      k8s-app: prometheus
  template:
    metadata:
      labels:
        k8s-app: prometheus
      annotations:
        scheduler.alpha.kubernetes.io/critical-pod: ''
    spec:
      priorityClassName: system-cluster-critical
      serviceAccountName: prometheus
      # 初始化容器
      initContainers:
      - name: "init-chown-data"
        image: "busybox:latest"
        imagePullPolicy: "IfNotPresent"
        command: ["chown", "-R", "65534:65534", "/data"]
        volumeMounts:
        - name: prometheus-data
          mountPath: /data
          subPath: ""
      containers:
        - name: prometheus-server-configmap-reload
          image: "jimmidyson/configmap-reload:v0.1"
          imagePullPolicy: "IfNotPresent"
          args:
            - --volume-dir=/etc/config
            - --webhook-url=http://localhost:9090/-/reload
          volumeMounts:
            - name: config-volume
              mountPath: /etc/config
              readOnly: true
          resources:
            limits:
              cpu: 10m
              memory: 10Mi
            requests:
              cpu: 10m
              memory: 10Mi

        - name: prometheus-server
          # 主要使用镜像
          image: "prom/prometheus:v2.2.1"
          imagePullPolicy: "IfNotPresent"
          args:
            - --config.file=/etc/config/prometheus.yml
            - --storage.tsdb.path=/data
            - --web.console.libraries=/etc/prometheus/console_libraries
            - --web.console.templates=/etc/prometheus/consoles
            - --web.enable-lifecycle
          ports:
            - containerPort: 9090
          readinessProbe:
            # 健康检查
            httpGet:
              path: /-/ready
              port: 9090
            initialDelaySeconds: 30
            timeoutSeconds: 30
          livenessProbe:
            httpGet:
              path: /-/healthy
              port: 9090
            initialDelaySeconds: 30
            timeoutSeconds: 30
          # based on 10 running nodes with 30 pods each
          resources:
            limits:
              cpu: 200m
              memory: 1000Mi
            requests:
              cpu: 200m
              memory: 1000Mi
          # 数据卷
          volumeMounts:
            - name: config-volume
              mountPath: /etc/config
            - name: prometheus-data
              mountPath: /data
              subPath: ""
            - name: prometheus-rules
              mountPath: /etc/config/rules
              subPath: ""
      terminationGracePeriodSeconds: 300
      volumes:
        - name: config-volume
          configMap:
            name: prometheus-config
        - name: prometheus-rules
          configMap:
            name: prometheus-rules
  volumeClaimTemplates:
  - metadata:
      name: prometheus-data
    spec:
      # 使用动态PV、修改为已创建的PV动态存储
      storageClassName: managed-nfs-storage
      accessModes:
        - ReadWriteOnce
      resources:
        requests:
          storage: "5Gi"

重新应用prometheus-statefulset.yaml

kubectl apply -f prometheus-statefulset.yaml