Konfigurieren Sie Prometheus und Grafana zur Überwachung von SUSE® Storage

 apiVersion: monitoring.coreos.com/v1
 kind: Alertmanager
 metadata:
   name: longhorn
   namespace: default
 spec:
   replicas: 3

 global:
   resolve_timeout: 5m
 route:
   group_by: [alertname]
   receiver: email_and_slack
 receivers:
 - name: email_and_slack
   email_configs:
   - to: <the email address to send notifications to>
     from: <the sender address>
     smarthost: <the SMTP host through which emails are sent>
     # SMTP authentication information.
     auth_username: <the username>
     auth_identity: <the identity>
     auth_password: <the password>
     headers:
       subject: 'Longhorn-Alert'
     text: |-
       {{ range .Alerts }}
         *Alert:* {{ .Annotations.summary }} - `{{ .Labels.severity }}`
         *Description:* {{ .Annotations.description }}
         *Details:*
         {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`
         {{ end }}
       {{ end }}
   slack_configs:
   - api_url: <the Slack webhook URL>
     channel: <the channel or user to send notifications to>
     text: |-
       {{ range .Alerts }}
         *Alert:* {{ .Annotations.summary }} - `{{ .Labels.severity }}`
         *Description:* {{ .Annotations.description }}
         *Details:*
         {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`
         {{ end }}
       {{ end }}

 $ kubectl create secret generic alertmanager-longhorn --from-file=alertmanager.yaml -n default

 apiVersion: v1
 kind: Service
 metadata:
   name: alertmanager-longhorn
   namespace: default
 spec:
   type: NodePort
   ports:
   - name: web
     nodePort: 30903
     port: 9093
     protocol: TCP
     targetPort: web
   selector:
     alertmanager: longhorn

 apiVersion: monitoring.coreos.com/v1
 kind: PrometheusRule
 metadata:
   labels:
     prometheus: longhorn
     role: alert-rules
   name: prometheus-longhorn-rules
   namespace: default
 spec:
   groups:
   - name: longhorn.rules
     rules:
     - alert: LonghornVolumeUsageCritical
       annotations:
         description: Longhorn volume {{$labels.volume}} on {{$labels.node}} is at {{$value}}% used for
           more than 5 minutes.
         summary: Longhorn volume capacity is over 90% used.
       expr: 100 * (longhorn_volume_usage_bytes / longhorn_volume_capacity_bytes) > 90
       for: 5m
       labels:
         issue: Longhorn volume {{$labels.volume}} usage on {{$labels.node}} is critical.
         severity: critical

 apiVersion: v1
 kind: ServiceAccount
 metadata:
   name: prometheus
   namespace: default

 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRole
 metadata:
   name: prometheus
   namespace: default
 rules:
 - apiGroups: [""]
   resources:
   - nodes
   - services
   - endpoints
   - pods
   verbs: ["get", "list", "watch"]
 - apiGroups: [""]
   resources:
   - configmaps
   verbs: ["get"]
 - nonResourceURLs: ["/metrics"]
   verbs: ["get"]

 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding
 metadata:
   name: prometheus
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: ClusterRole
   name: prometheus
 subjects:
 - kind: ServiceAccount
   name: prometheus
   namespace: default

 apiVersion: monitoring.coreos.com/v1
 kind: Prometheus
 metadata:
   name: longhorn
   namespace: default
 spec:
   replicas: 2
   serviceAccountName: prometheus
   alerting:
     alertmanagers:
       - namespace: default
         name: alertmanager-longhorn
         port: web
   serviceMonitorSelector:
     matchLabels:
       name: longhorn-prometheus-servicemonitor
   ruleSelector:
     matchLabels:
       prometheus: longhorn
       role: alert-rules

 apiVersion: v1
 kind: Service
 metadata:
   name: prometheus-longhorn
   namespace: default
 spec:
   type: NodePort
   ports:
   - name: web
     nodePort: 30904
     port: 9090
     protocol: TCP
     targetPort: web
   selector:
     prometheus: longhorn

 apiVersion: v1
 kind: ConfigMap
 metadata:
   name: grafana-datasources
   namespace: default
 data:
   prometheus.yaml: |-
     {
         "apiVersion": 1,
         "datasources": [
             {
                "access":"proxy",
                 "editable": true,
                 "name": "prometheus-longhorn",
                 "orgId": 1,
                 "type": "prometheus",
                 "url": "http://prometheus-longhorn.default.svc:9090",
                 "version": 1
             }
         ]
     }

 apiVersion: apps/v1
 kind: Deployment
 metadata:
   name: grafana
   namespace: default
   labels:
     app: grafana
 spec:
   replicas: 1
   selector:
     matchLabels:
       app: grafana
   template:
     metadata:
       name: grafana
       labels:
         app: grafana
     spec:
       containers:
       - name: grafana
         image: grafana/grafana:7.1.5
         ports:
         - name: grafana
           containerPort: 3000
         resources:
           limits:
             memory: "500Mi"
             cpu: "300m"
           requests:
             memory: "500Mi"
             cpu: "200m"
         volumeMounts:
           - mountPath: /var/lib/grafana
             name: grafana-storage
           - mountPath: /etc/grafana/provisioning/datasources
             name: grafana-datasources
             readOnly: false
       volumes:
         - name: grafana-storage
           emptyDir: {}
         - name: grafana-datasources
           configMap:
               defaultMode: 420
               name: grafana-datasources

 apiVersion: v1
 kind: Service
 metadata:
   name: grafana
   namespace: default
 spec:
   selector:
     app: grafana
   type: ClusterIP
   ports:
     - port: 3000
       targetPort: 3000

 kubectl -n default patch svc grafana --type='json' -p '[{"op":"replace","path":"/spec/type","value":"NodePort"},{"op":"replace","path":"/spec/ports/0/nodePort","value":32000}]'

 # Default Credential
 User: admin
 Pass: admin