Prometheus K8S中部署Alertmanager

Prometheus K8S中部署Alertmanager

设置告警和通知的主要步骤如下：
一、部署Alertmanager
二、配置Prometheus与Alertmanager通信
三、配置告警
　　1. prometheus指定rules目录
　　2. configmap存储告警规则
　　3. configmap挂载到容器rules目录

一、部署Alertmanager

配置文件

已经修改好的配置文件

• # 存储主配置文件
• alertmanager-configmap.yaml

• apiVersion: v1
  kind: ConfigMap
  metadata:
    # 配置文件名称
    name: alertmanager-config
    namespace: kube-system
    labels:
      kubernetes.io/cluster-service: "true"
      addonmanager.kubernetes.io/mode: EnsureExists
  data:
    alertmanager.yml: |
      global: 
        resolve_timeout: 5m
        # 告警自定义邮件
        smtp_smarthost: 'smtp.163.com:25'
        smtp_from: 'baojingtongzhi@163.com'
        smtp_auth_username: 'baojingtongzhi@163.com'
        smtp_auth_password: 'liang123'
  
      receivers:
      - name: default-receiver
        email_configs:
        - to: "zhenliang369@163.com"
  
      route:
        group_interval: 1m
        group_wait: 10s
        receiver: default-receiver
        repeat_interval: 1m

• # 部署核心组件
• 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

• # 使用的自动PV存储
• 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:
    # 使用自己的动态PV
    storageClassName: managed-nfs-storage 
    accessModes:
      - ReadWriteOnce
    resources:
      requests:
        storage: "2Gi"

• # 暴露Prot端口
• alertmanager-service.yaml

• apiVersion: v1
  kind: PersistentVolumeClaim
  metadata:
    name: alertmanager
    namespace: kube-system
    labels:
      kubernetes.io/cluster-service: "true"
      addonmanager.kubernetes.io/mode: EnsureExists
  spec:
    # 使用自己的动态PV
    storageClassName: managed-nfs-storage 
    accessModes:
      - ReadWriteOnce
    resources:
      requests:
        storage: "2Gi"
  [root@Master1 ~]# cat 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"

部署

1、创建pvc、configmap、deployment、service

kubectl apply -f alertmanager-pvc.yaml
kubectl create -f alertmanager-configmap.yaml
kubectl apply -f alertmanager-deployment.yaml
kubectl apply -f alertmanager-service.yaml

2、查看Pod状态

kubectl get pod -n kube-system

NAME READY STATUS RESTARTS AGE
alertmanager-5bb796cb48-fwztv 2/2 Running 0 2m29s

3、查看service状态
kubectl get svc -n kube-system

NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
alertmanager ClusterIP 10.0.0.126 <none> 80/TCP

二、配置Prometheus与Alertmanager通信

1、编辑 prometheus-configmap.yaml 配置文件添加绑定信息

# Prometheus configuration format https://prometheus.io/docs/prometheus/latest/configuration/configuration/
apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-config
  namespace: kube-system 
  labels:
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: EnsureExists
data:
  # 存放prometheus配置文件
  prometheus.yml: |
    # 配置采集目标
    scrape_configs:
    - job_name: prometheus
      static_configs:
      - targets:
        # 采集自身
        - localhost:9090

  prometheus.yml: |
    # 配置采集目标
    scrape_configs:
    - job_name: kubernetes-nodes
      static_configs:
      - targets:
        # 采集自身
        - 192.168.1.110:9100
        - 192.168.1.111:9100
    
    # 采集：Apiserver 生存指标
    # 创建的job name 名称为 kubernetes-apiservers
    - job_name: kubernetes-apiservers
      # 基于k8s的服务发现
      kubernetes_sd_configs:
      - role: endpoints
      # 使用通信标记标签
      relabel_configs:
      # 保留正则匹配标签
      - action: keep
        # 已经包含
        regex: default;kubernetes;https
        source_labels:
        - __meta_kubernetes_namespace
        - __meta_kubernetes_service_name
        - __meta_kubernetes_endpoint_port_name
      # 使用方法为https、默认http
      scheme: https
      tls_config:
        # promethus访问Apiserver使用认证
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        # 跳过https认证
        insecure_skip_verify: true
      # promethus访问Apiserver使用认证
      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
 
    # 采集：Kubelet 生存指标
    - job_name: kubernetes-nodes-kubelet
      kubernetes_sd_configs:
      # 发现集群中所有的Node
      - role: node
      relabel_configs:
      # 通过regex获取关键信息
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
      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

    # 采集：nodes-cadvisor 信息
    - job_name: kubernetes-nodes-cadvisor
      kubernetes_sd_configs:
      - role: node
      relabel_configs:
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
      # 重命名标签
      - target_label: __metrics_path__
        replacement: /metrics/cadvisor
      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

    # 采集：service-endpoints 信息
    - job_name: kubernetes-service-endpoints
      # 选定指标
      kubernetes_sd_configs:
      - role: endpoints
      relabel_configs:
      - action: keep
        regex: true
        # 指定源标签
        source_labels:
        - __meta_kubernetes_service_annotation_prometheus_io_scrape
      - action: replace
        regex: (https?)
        source_labels:
        - __meta_kubernetes_service_annotation_prometheus_io_scheme
        # 重命名标签采集
        target_label: __scheme__
      - action: replace
        regex: (.+)
        source_labels:
        - __meta_kubernetes_service_annotation_prometheus_io_path
        target_label: __metrics_path__
      - action: replace
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
        source_labels:
        - __address__
        - __meta_kubernetes_service_annotation_prometheus_io_port
        target_label: __address__
      - action: labelmap
        regex: __meta_kubernetes_service_label_(.+)
      - action: replace
        source_labels:
        - __meta_kubernetes_namespace
        target_label: kubernetes_namespace
      - action: replace
        source_labels:
        - __meta_kubernetes_service_name
        target_label: kubernetes_name

    # 采集：kubernetes-services 服务指标
    - job_name: kubernetes-services
      kubernetes_sd_configs:
      - role: service
      # 黑盒探测，探测IP与端口是否可用
      metrics_path: /probe
      params:
        module:
        - http_2xx
      relabel_configs:
      - action: keep
        regex: true
        source_labels:
        - __meta_kubernetes_service_annotation_prometheus_io_probe
      - source_labels:
        - __address__
        target_label: __param_target
      # 使用 blackbox进行黑盒探测
      - replacement: blackbox
        target_label: __address__
      - source_labels:
        - __param_target
        target_label: instance
      - action: labelmap
        regex: __meta_kubernetes_service_label_(.+)
      - source_labels:
        - __meta_kubernetes_namespace
        target_label: kubernetes_namespace
      - source_labels:
        - __meta_kubernetes_service_name
        target_label: kubernetes_name

    # 采集： kubernetes-pods 信息
    - job_name: kubernetes-pods
      kubernetes_sd_configs:
      - role: pod
      relabel_configs:
      - action: keep
        regex: true
        source_labels:
        # 只保留采集的信息
        - __meta_kubernetes_pod_annotation_prometheus_io_scrape
      - action: replace
        regex: (.+)
        source_labels:
        - __meta_kubernetes_pod_annotation_prometheus_io_path
        target_label: __metrics_path__
      - action: replace
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
        source_labels:
        # 采集地址
        - __address__
        # 采集端口 
        - __meta_kubernetes_pod_annotation_prometheus_io_port
        target_label: __address__
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
      - action: replace
        source_labels:
        - __meta_kubernetes_namespace
        target_label: kubernetes_namespace
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_name
        target_label: kubernetes_pod_name
    alerting:
      # 告警配置文件
      alertmanagers:
      # 修改：使用静态绑定
      - static_configs:
          # 修改：targets、指定地址与端口
          - targets: ["alertmanager:80"]

2、应用加载配置文件

kubectl apply -f prometheus-configmap.yaml

3、web控制台查看配置是否生效

http://192.168.1.110:42575/config

三、配置告警

1. prometheus指定rules目录

1、编辑 prometheus-configmap.yaml 添加报警信息

apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-config
  namespace: kube-system
  labels:
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: EnsureExists
data:
  prometheus.yml: |
    # 添加：指定读取rules配置
    rules_files:
    - /etc/config/rules/*.rules
......

2、生效配置文件

kubectl apply -f prometheus-configmap.yaml

2. configmap存储告警规则

1、创建yaml文件同过configmap存储告警规则
vim prometheus-rules.yaml

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 }})"

3. configmap挂载到容器rules目录

1、修改挂载点位置，使用之前部署的prometheus动态PV

vim prometheus-statefulset.yaml

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
            # 添加：指定rules的configmap配置文件名称
            - name: prometheus-rules
              mountPath: /etc/config/rules
              subPath: ""
      terminationGracePeriodSeconds: 300
      volumes:
        - name: config-volume
          configMap:
            name: prometheus-config
        # 添加：name rules
        - name: prometheus-rules
          # 添加：配置文件
          configMap:
            # 添加：定义文件名称
            name: prometheus-rules

  volumeClaimTemplates:
  - metadata:
      name: prometheus-data
    spec:
      # 使用动态PV
      storageClassName: managed-nfs-storage 
      accessModes:
        - ReadWriteOnce
      resources:
        requests:
          storage: "16Gi"

2、创建configmap并更新PV

kubectl apply -f prometheus-rules.yaml
kubectl apply -f prometheus-statefulset.yaml 

3、查看Pod
kubectl get pod -n kube-system

NAME READY STATUS RESTARTS AGE
prometheus-0 1/2 Running 0 42s