Add Prometheus and Grafana services with alerting configuration

rules.yml

@@ -0,0 +1,36 @@
+groups:
+  - name: recording_rules
+    rules:
+      - record: job:up:sum
+        expr: sum(up) by (job)
+      - record: job:up:count
+        expr: count(up) by (job)
+
+  - name: alerting_rules
+    rules:
+      - alert: InstanceDown
+        expr: up == 0
+        for: 5m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Instance {{ $labels.instance }} down"
+          description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes."
+
+      - alert: TraefikDown
+        expr: up{job="traefik"} == 0
+        for: 2m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Traefik is down"
+          description: "Traefik has been down for more than 2 minutes."
+
+      - alert: AutheliaDown
+        expr: up{job="authelia"} == 0
+        for: 5m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Authelia is down"
+          description: "Authelia authentication service is unavailable."