alertmanager.yaml

apiVersion: v1
kind: Template
metadata:
  name: alertmanager
  annotations:
    "openshift.io/display-name": Prometheus Alert Manager
    description: |
      A monitoring solution for an OpenShift cluster - collect and gather metrics from nodes, services, and the infrastructure. This component provides the Alert Manager.
    iconClass: icon-cogs
    tags: "monitoring,prometheus,alertmanager,time-series"
parameters:
- description: The location of the prometheus image
  name: IMAGE_ALERTMANAGER
  value: wkulhanek/alertmanager:latest
- name: VOLUME_CAPACITY
  displayName: Volume Capacity
  description: Volume space available for data, e.g. 512Mi, 2Gi.
  value: 4Gi
  required: true
- name: WEBHOOK_URL
  displayName: Webhook URL
  description: URL for the Webhook to send alerts.
  required: true
objects:
- apiVersion: v1
  kind: Route
  metadata:
    name: alertmanager
  spec:
    to:
      name: alertmanager
- apiVersion: v1
  kind: Service
  metadata:
    annotations:
      prometheus.io/scrape: "true"
      prometheus.io/scheme: http
    labels:
      name: alertmanager
    name: alertmanager
  spec:
    ports:
    - name: alertmanager
      port: 9093
      protocol: TCP
      targetPort: 9093
    selector:
      app: alertmanager
- apiVersion: v1
  kind: DeploymentConfig
  metadata:
    labels:
      app: alertmanager
    name: alertmanager
  spec:
    replicas: 1
    selector:
      app: alertmanager
      deploymentconfig: alertmanager
    template:
      metadata:
        labels:
          app: alertmanager
          deploymentconfig: alertmanager
        name: alertmanager
      spec:
        containers:
        - name: alertmanager
          args:
          - --config.file=/etc/alertmanager/config.yml
          - --storage.path=/alertmanager
          image: ${IMAGE_ALERTMANAGER}
          imagePullPolicy: IfNotPresent
          livenessProbe:
            failureThreshold: 3
            httpGet:
              path: /#/status
              port: 9093
              scheme: HTTP
            initialDelaySeconds: 2
            periodSeconds: 10
            successThreshold: 1
            timeoutSeconds: 1
          readinessProbe:
            failureThreshold: 3
            httpGet:
              path: /#/status
              port: 9093
              scheme: HTTP
            initialDelaySeconds: 2
            periodSeconds: 10
            successThreshold: 1
            timeoutSeconds: 1

          volumeMounts:
          - mountPath: /etc/alertmanager
            name: config-volume
          - mountPath: /alertmanager
            name: data-volume
        restartPolicy: Always
        volumes:
        - name: data-volume
          persistentVolumeClaim:
            claimName: alertmanager-data-pvc
        - configMap:
            name: alertmanager
          name: config-volume
- apiVersion: v1
  kind: PersistentVolumeClaim
  metadata:
    name: alertmanager-data-pvc
  spec:
    accessModes:
    - ReadWriteMany
    resources:
      requests:
        storage: "${VOLUME_CAPACITY}"
- apiVersion: v1
  kind: ConfigMap
  metadata:
    name: alertmanager
  data:
    config.yml: |
      global:

      # The root route on which each incoming alert enters.
      route:
        # The root route must not have any matchers as it is the entry point for
        # all alerts. It needs to have a receiver configured so alerts that do not
        # match any of the sub-routes are sent to someone.
        receiver: 'webhook'

        # The labels by which incoming alerts are grouped together. For example,
        # multiple alerts coming in for cluster=A and alertname=LatencyHigh would
        # be batched into a single group.
        group_by: ['alertname', 'cluster']

        # When a new group of alerts is created by an incoming alert, wait at
        # least 'group_wait' to send the initial notification.
        # This way ensures that you get multiple alerts for the same group that start
        # firing shortly after another are batched together on the first
        # notification.
        group_wait: 30s

        # When the first notification was sent, wait 'group_interval' to send a batch
        # of new alerts that started firing for that group.
        group_interval: 5m

        # If an alert has successfully been sent, wait 'repeat_interval' to
        # resend them.
        repeat_interval: 3h

      receivers:
      - name: 'webhook'
        webhook_configs:
        - send_resolved: true
          url: '${WEBHOOK_URL}'