Initial commit: homelab configuration and documentation

monitoring/grafana/alert_rules.yml

@@ -0,0 +1,63 @@
+groups:
+  - name: homelab_alerts
+    interval: 30s
+    rules:
+      # CPU Usage Alert
+      - alert: HighCPUUsage
+        expr: 100 - (avg by (instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High CPU usage detected on {{ $labels.instance }}"
+          description: "CPU usage is above 80% (current value: {{ $value }}%)"
+
+      # Memory Usage Alert
+      - alert: HighMemoryUsage
+        expr: (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100 > 85
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High memory usage detected on {{ $labels.instance }}"
+          description: "Memory usage is above 85% (current value: {{ $value }}%)"
+
+      # Disk Usage Alert
+      - alert: HighDiskUsage
+        expr: (1 - (node_filesystem_avail_bytes{fstype!~"tmpfs|fuse.lxcfs"} / node_filesystem_size_bytes{fstype!~"tmpfs|fuse.lxcfs"})) * 100 > 80
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High disk usage detected on {{ $labels.instance }}"
+          description: "Disk usage on {{ $labels.mountpoint }} is above 80% (current value: {{ $value }}%)"
+
+      # Node Down Alert
+      - alert: NodeDown
+        expr: up{job="node-exporter"} == 0
+        for: 2m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Node {{ $labels.instance }} is down"
+          description: "Node exporter on {{ $labels.instance }} has been down for more than 2 minutes"
+
+      # Container Down Alert
+      - alert: ContainerDown
+        expr: up{job="docker"} == 0
+        for: 2m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Container {{ $labels.instance }} is down"
+          description: "Docker container on {{ $labels.instance }} has been down for more than 2 minutes"
+
+      # Disk I/O Alert (high wait time)
+      - alert: HighDiskIOWait
+        expr: rate(node_cpu_seconds_total{mode="iowait"}[5m]) * 100 > 20
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High disk I/O wait on {{ $labels.instance }}"
+          description: "Disk I/O wait time is above 20% (current value: {{ $value }}%)"