save

templates/monitoring/alerts/infrastructure.yml

@@ -0,0 +1,56 @@
+groups:
+  - name: infrastructure
+    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: HighCpuUsage
+        expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High CPU usage on {{ $labels.instance }}"
+          description: "CPU usage is above 80% on {{ $labels.instance }} for more than 5 minutes."
+
+      - alert: HighMemoryUsage
+        expr: (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100 > 90
+        for: 5m
+        labels:
+          severity: critical
+        annotations:
+          summary: "High memory usage on {{ $labels.instance }}"
+          description: "Memory usage is above 90% on {{ $labels.instance }} for more than 5 minutes."
+
+      - alert: DiskSpaceLow
+        expr: (1 - (node_filesystem_avail_bytes{fstype!="tmpfs"} / node_filesystem_size_bytes{fstype!="tmpfs"})) * 100 > 85
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Low disk space on {{ $labels.instance }}"
+          description: "Disk usage is above 85% on {{ $labels.instance }} ({{ $labels.mountpoint }})"
+
+      - alert: DiskSpaceCritical
+        expr: (1 - (node_filesystem_avail_bytes{fstype!="tmpfs"} / node_filesystem_size_bytes{fstype!="tmpfs"})) * 100 > 95
+        for: 2m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Critical disk space on {{ $labels.instance }}"
+          description: "Disk usage is above 95% on {{ $labels.instance }} ({{ $labels.mountpoint }})"
+
+      - alert: HighLoadAverage
+        expr: node_load1 > (count by(instance) (node_cpu_seconds_total{mode="idle"})) * 0.8
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High load average on {{ $labels.instance }}"
+          description: "Load average is high on {{ $labels.instance }}: {{ $value }}"