feat(monitoring): add prometheus metrics, alerts, and dashboard for taupi fan

2026-07-03 11:28:36 +02:00
parent 1ad356a7b4
commit 6627372ec0
3 changed files with 420 additions and 68 deletions
@@ -0,0 +1,83 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: taupi-fan
+  namespace: monitoring
+  labels:
+    app: taupi-fan
+spec:
+  ports:
+    - name: http-metrics
+      port: 80
+      targetPort: 80
+---
+apiVersion: v1
+kind: Endpoints
+metadata:
+  name: taupi-fan
+  namespace: monitoring
+  labels:
+    app: taupi-fan
+subsets:
+  - addresses:
+      - ip: 192.168.10.168
+    ports:
+      - name: http-metrics
+        port: 80
+---
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: taupi-fan
+  namespace: monitoring
+  labels:
+    app: taupi-fan
+    release: prometheus-operator
+spec:
+  selector:
+    matchLabels:
+      app: taupi-fan
+  namespaceSelector:
+    matchNames:
+      - monitoring
+  endpoints:
+    - port: http-metrics
+      path: /script/1/prometheus
+      interval: 30s
+      scrapeTimeout: 10s
+---
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: taupi-fan-alerts
+  namespace: monitoring
+  labels:
+    release: prometheus-operator
+spec:
+  groups:
+    - name: taupi-fan.rules
+      rules:
+        - alert: TaupiFanOffline
+          expr: up{job="taupi-fan"} == 0
+          for: 5m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Id: {{ $labels.instance }} - TAUPI Fan Plug is unreachable"
+            description: "The Shelly plug at 192.168.10.168 is unreachable by Prometheus. Check Wi-Fi connection or power status."
+        - alert: TaupiFanSensorsStale
+          expr: taupi_lost_connection_seconds_innen > 600 or taupi_lost_connection_seconds_aussen > 600
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "TAUPI Fan BLE sensors stale"
+            description: "The BLE sensors for temperature and humidity inside or outside have not sent new data for over 10 minutes."
+        - alert: TaupiFanMoldDanger
+          expr: taupi_is_critical == 1
+          for: 30m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Cellar mold risk detected"
+            description: "The cellar relative humidity has exceeded the critical mold threshold (inside humidity is high enough that mold can grow on cold wall surfaces)."