Add prometheus/alert.rules.yml

prometheus/alert.rules.yml

@@ -0,0 +1,40 @@
+groups:
+  - name: instance-health
+    rules:
+      - alert: InstanceDown
+        expr: up == 0
+        for: 5m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Instance {{ $labels.instance }} down"
+          description: "{{ $labels.job }} on {{ $labels.instance }} has been down for more than 5 minutes."
+
+  - name: host-health
+    rules:
+      - alert: HighCPULoad
+        expr: avg(rate(node_cpu_seconds_total{mode!="idle"}[5m])) by (instance) > 0.85
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High CPU load on {{ $labels.instance }}"
+          description: "Average CPU usage > 85% for 10m."
+
+      - alert: HighMemoryUsage
+        expr: (node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes > 0.9
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High memory usage on {{ $labels.instance }}"
+          description: "Memory usage > 90% for 10m."
+
+      - alert: DiskSpaceLow
+        expr: (node_filesystem_size_bytes{fstype!~"tmpfs|overlay"} - node_filesystem_free_bytes{fstype!~"tmpfs|overlay"}) / node_filesystem_size_bytes{fstype!~"tmpfs|overlay"} > 0.85
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Disk getting full on {{ $labels.instance }}"
+          description: "Disk usage > 85% on {{ $labels.mountpoint }}."