一、部署Alertmanager

官网参考地址：https://github.com/prometheus/alertmanager

配置文件

1.alertmanager主配置文件

[root@localhost alertmanager]# cat 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: 1m
      # 告警自定义邮件
      smtp_smarthost: 'smtp.sina.com.cn:25'
      smtp_from: 'xxx@sina.com'
      smtp_auth_username: 'xxx@sina.com'
      smtp_auth_password: '123456789'
      smtp_require_tls: false

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

    route:
      group_interval: 1m
      group_wait: 10s
      receiver: default-receiver
      repeat_interval: 1m
[root@localhost alertmanager]#

alertmanager-configmap.yaml

2.部署核心组件

[root@localhost alertmanager]# cat 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"
          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
          emptyDir: {}
[root@localhost alertmanager]#

alertmanager-deployment.yaml

这里没有采用pv自动存储模式，原yaml文件参考以下

#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"

自动pv部署

3.暴露Prot端口

[root@localhost alertmanager]# 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: NodePort
[root@localhost alertmanager]#

alertmanager-service.yaml

部署

1、创建configmap、deployment、service
kubectl create -f alertmanager-configmap.yaml
kubectl apply -f alertmanager-deployment.yaml
kubectl apply -f alertmanager-service.yaml

2、查看

二、配置Prometheus与Alertmanager通信

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

[root@localhost alertmanager]# cd ../prometheus/
[root@localhost prometheus]# ls
configmap.yaml  configmap.yaml.bak  prometheus.deploy.yml  prometheus.deploy.yml.bak  prometheus-rules.yaml  prometheus.svc.yml  rbac-setup.yaml
[root@localhost prometheus]# cat configmap.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-config
  namespace: kube-system
data:
  prometheus.yml: |
    global:
      scrape_interval:     15s
      evaluation_interval: 15s
    scrape_configs:

    - job_name: 'kubernetes-apiservers'
      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_configs:
      - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
        action: keep
        regex: default;kubernetes;https

    - job_name: 'kubernetes-nodes'
      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

    - job_name: 'kubernetes-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-service-endpoints'
      kubernetes_sd_configs:
      - role: endpoints
      relabel_configs:
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
        action: keep
        regex: true
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
        action: replace
        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

    - job_name: 'kubernetes-services'
      kubernetes_sd_configs:
      - role: service
      metrics_path: /probe
      params:
        module: [http_2xx]
      relabel_configs:
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_probe]
        action: keep
        regex: true
      - source_labels: [__address__]
        target_label: __param_target
      - target_label: __address__
        replacement: blackbox-exporter.example.com:9115
      - 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

    - job_name: 'kubernetes-ingresses'
      kubernetes_sd_configs:
      - role: ingress
      relabel_configs:
      - source_labels: [__meta_kubernetes_ingress_annotation_prometheus_io_probe]
        action: keep
        regex: true
      - source_labels: [__meta_kubernetes_ingress_scheme,__address__,__meta_kubernetes_ingress_path]
        regex: (.+);(.+);(.+)
        replacement: ${1}://${2}${3}
        target_label: __param_target
      - target_label: __address__
        replacement: blackbox-exporter.example.com:9115
      - source_labels: [__param_target]
        target_label: instance
      - action: labelmap
        regex: __meta_kubernetes_ingress_label_(.+)
      - source_labels: [__meta_kubernetes_namespace]
        target_label: kubernetes_namespace
      - source_labels: [__meta_kubernetes_ingress_name]
        target_label: kubernetes_name

    - job_name: 'kubernetes-pods'
      kubernetes_sd_configs:
      - role: pod
      relabel_configs:
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
        action: keep
        regex: true
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
        action: replace
        target_label: __metrics_path__
        regex: (.+)
      - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
        action: replace
        regex: ([^:]+)(?::d+)?;(d+)
        replacement: $1:$2
        target_label: __address__
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
      - source_labels: [__meta_kubernetes_namespace]
        action: replace
        target_label: kubernetes_namespace
      - source_labels: [__meta_kubernetes_pod_name]
        action: replace
        target_label: kubernetes_pod_name
    - job_name: 'Linux'
      static_configs:
        - targets: ['node-exporter:9100']
          labels:
            instance: Linux-node




    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"]
    rule_files:
      - "/opt/rules/*.rules"
[root@localhost prometheus]#

prometheus配置文件

2、生效配置文件
kubectl apply -f configmap.yaml

3、web控制台查看配置是否生效

http://172.20.51.105:30003/config

三、配置告警

1. prometheus指定rules目录

2. configmap存储告警规则

[root@localhost prometheus]# ls
configmap.yaml  configmap.yaml.bak  prometheus.deploy.yml  prometheus.deploy.yml.bak  prometheus-rules.yaml  prometheus.svc.yml  rbac-setup.yaml
[root@localhost prometheus]# cat prometheus-rules.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  name: rules-config
  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 > 1
        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 }})"
[root@localhost prometheus]#

prometheus-rules.yaml

3. configmap挂载到容器rules目录

4. 生效配置

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

四、查看告警结果

故意将内存阈值设置小，为了演示告警

Alertmanager告警信息

Prometheus告警信息

邮件告警信息