feat(longhorn): add alerts and service monitor

cluster/apps/monitoring/grafana/helm-release.yaml

@@ -129,6 +129,11 @@ spec:
         cert-manager:
           url: https://raw.githubusercontent.com/monitoring-mixins/website/master/assets/cert-manager/dashboards/cert-manager.json
           datasource: Victoria
+        longhorn:
+          # renovate: depName="Longhorn"
+          gnetId: 16888
+          revision: 8
+          datasource: Victoria
         spegel:
           # renovate: depName="Spegel"
           gnetId: 18089

cluster/core/storage/longhorn/alerts.yaml

@@ -0,0 +1,21 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: prometheus-longhorn-rules
+  namespace: longhorn-system
+  labels:
+    release: kube-prometheus-stack
+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

cluster/core/storage/longhorn/kustomization.yaml

@@ -3,4 +3,6 @@ kind: Kustomization
 resources:
 - ./namespace.yaml
 - ./helm-repository.yaml
-- ./helm-release.yaml
+- ./helm-release.yaml
+- ./alerts.yaml
+- ./service-monitor.yaml

cluster/core/storage/longhorn/service-monitor.yaml

@@ -0,0 +1,13 @@
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: longhorn
+  namespace: longhorn-system
+  labels:
+    release: kube-prometheus-stack
+spec:
+  selector:
+    matchLabels:
+      app: longhorn-manager
+  endpoints:
+  - port: manager