Add monitoring stack (prometheus/alertmanager/grafana)

monitoring/rules/base-alerts.yml

@@ -0,0 +1,38 @@
+groups:
+  - name: base-alerts
+    rules:
+      - alert: InstanceDown
+        expr: up == 0
+        for: 2m
+        labels:
+          severity: critical
+        annotations:
+          summary: "{{ $labels.instance }} down"
+          description: "{{ $labels.job }} on {{ $labels.instance }} is not responding"
+
+      - alert: HighCPU
+        expr: (1 - avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m]))) > 0.90
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High CPU on {{ $labels.instance }}"
+          description: "CPU usage > 90% for 10m"
+
+      - alert: HighMemory
+        expr: (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) > 0.90
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High memory on {{ $labels.instance }}"
+          description: "Memory usage > 90% for 10m"
+
+      - alert: DiskFull
+        expr: (node_filesystem_avail_bytes{fstype!~"tmpfs|overlay"} / node_filesystem_size_bytes{fstype!~"tmpfs|overlay"}) < 0.10
+        for: 15m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Disk low on {{ $labels.instance }}"
+          description: "<10% free on {{ $labels.mountpoint }}"