Prometheus监控告警

alert是一个单独的模块，需要我们单独的配置

需要声明邮箱地址，配置是以ConfigMap进行配置

alertmanager也是pod部署，部署在k8s集群

inactive表示已经激活的告警指标

pending告警的阀值已经触发，正在等待发送邮件

firing表示告警项已经触发了发送配置（有家，短信，电话，钉钉告警）

apiVersion: v1
kind: ConfigMap
metadata:
  name: alertmanager
  namespace: monitor-sa
data:
  alertmanager.yml: |-
    global:
      resolve_timeout: 1m
#定义告警想项发送邮件的超时时间
      smtp_smarthost: 'smtp.qq.com:25'
      smtp_from: '2040756255@qq.com'
      smtp_auth_username: '2040756255@qq.com'
      smtp_require_password: 'dfzodxequrrbjhdj'
#设置告警的分发策略
    route:
      group_by: [alertname]
#分组依据，分组名称
      group_wait: 10s
#组告警的等待时间，也就是告警产生后等待10s，如果同组内有其他的告警，一起发出
      group_interval: 10s
#上下两个组发送告警的间隔时间
      receiver: default-receiver
#定义由谁来收告警
    receivers:
    - name: 'default-receiver'
      email_configs:
      - to: '2040756255@qq.com'
#设置告警邮件的收件人地址
        send_resolved: true



apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus-server
  namespace: monitor-sa
  labels:
    app: prometheus
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus
      component: server
  template:
    metadata:
      labels:
        app: prometheus
        component: server
      annotations:
        prometheus.io/scrape: 'false'
    spec:
      serviceAccountName: monitor
      initContainers:
      - name: init-chmod
        image: busybox:latest
        command: ['sh','-c','chmod -R 777 /prometheus;chmod -R 777 /etc']
        volumeMounts:
        - mountPath: /prometheus
          name: prometheus-storage-volume
        - mountPath: /etc/localtime
          name: timezone
      containers:
      - name: prometheus
        image: prom/prometheus:v2.45.0
        command:
          - prometheus
          - --config.file=/etc/prometheus/prometheus.yml
          - --storage.tsdb.path=/prometheus
          - --storage.tsdb.retention=720h
          - --web.enable-lifecycle
        ports:
        - containerPort: 9090
        volumeMounts:
        - name: prometheus-config
          mountPath: /etc/prometheus/
        - mountPath: /prometheus/
          name: prometheus-storage-volume
        - name: timezone
          mountPath: /etc/localtime
        - name: k8s-certs
          mountPath: /var/run/secrets/kubernetes.io/k8s-certs/etcd/
      - name: alertmanager
        image: prom/alertmanager:v0.20.0
        args:
        - "--config.file=/etc/alertmanager/alertmanager.yml"
        - "--log.level=debug"
        ports:
        - containerPort: 9093
          protocol: TCP
          name: alertmanager
        volumeMounts:
        - name: alertmanager-config
          mountPath: /etc/alertmanager
        - name: alertmanager-storage
          mountPath: /alertmanager
        - name: localtime
          mountPath: /etc/localtime
      volumes:
        - name: prometheus-config
          configMap:
            name: prometheus-config
            defaultMode: 0777
        - name: prometheus-storage-volume
          hostPath:
            path: /data
            type: Directory
        - name: k8s-certs
          secret:
            secretName: etcd-certs
        - name: timezone
          hostPath:
            path: /usr/share/zoneinfo/Asia/Shanghai
        - name: alertmanager-config
          configMap:
            name: alertmanager
        - name: alertmanager-storage
          hostPath:
            path: /data/alertmanager
            type: DirectoryOrCreate
        - name: localtime
          hostPath:
            path: /usr/share/zoneinfo/Asia/Shanghai


kind: ConfigMap
apiVersion: v1
metadata:
  labels:
    app: prometheus
  name: prometheus-config
  namespace: monitor-sa
data:
  prometheus.yml: |
    rule_files:
    - /etc/prometheus/rules.yml
    alerting:
      alertmanagers:
      - static_configs:
        - targets: ["localhost:9093"]
    global:
      scrape_interval: 15s
      scrape_timeout: 10s
      evaluation_interval: 1m
    scrape_configs:
    - job_name: 'kubernetes-node'
      kubernetes_sd_configs:
      - role: node
      relabel_configs:
      - source_labels: [__address__]
        regex: '(.*):10250'
        replacement: '${1}:9100'
        target_label: __address__
        action: replace
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
    - job_name: 'kubernetes-node-cadvisor'
      kubernetes_sd_configs:
      - role:  node
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
      relabel_configs:
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
      - target_label: __address__
        replacement: kubernetes.default.svc:443
      - source_labels: [__meta_kubernetes_node_name]
        regex: (.+)
        target_label: __metrics_path__
        replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
    - job_name: 'kubernetes-apiserver'
      kubernetes_sd_configs:
      - role: endpoints
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
      relabel_