Add DWPD alerts

stackhpc · Oct 13, 2023 · c474ca9 · c474ca9
1 parent 95d88fb
commit c474ca9
Showing 1 changed file with 17 additions and 1 deletion.
diff --git a/etc/kayobe/kolla/config/prometheus/smart.rules b/etc/kayobe/kolla/config/prometheus/smart.rules
@@ -13,4 +13,20 @@ groups:
       summary: "SMART monitor reports bad disk on (instance {{ $labels.instance }})"
       description: "{{ $labels.instance }} is reporting unhealthy for the disk at {{ $labels.disk }}. Disk serial number is: {{ $labels.serial_number }}"
 
-{% endraw %}
+  - alert: DWPDTooHigh
+    expr: (delta(nvme_data_units_written_total[168h])*512000 / nvme_physical_size_bytes)/7 > 1
+    labels:
+      severity: alert
+    annotations:
+      summary: "High 7-Day Average DWPD for {{ $labels.instance }}
+      description: "The 7-Day average for Disk Writes Per Day for disk {{ $labels.device }} on {{ $labels.instance }} exceeds 1 DWPD"
+
+  - alert: DWPDTooHighWarning
+    expr: delta(nvme_data_units_written_total[24h])*512000 / nvme_physical_size_bytes > 1
+    labels:
+      severity: warning
+    annotations:
+      summary: "High DWPD for {{ $labels.instance }}
+      description: "The 24-Hour average for Disk Writes Per Day for disk {{ $labels.device }} on {{ $labels.instance }} exceeds 1 DWPD"
+
+{% endraw %}