Merge pull request #1911 from stackhpc/alert-on-radosgw-usage-exporter

Add alerting for RadosGW Usage Exporter metrics

Author: MoteHue

etc/kayobe/kolla/config/prometheus/ceph.rules

@@ -205,3 +205,14 @@ groups:
       description: "{{ $value }} OSD requests are taking too long to process (osd_op_complaint_time exceeded)"
 
 {% endraw %}
+{% if stackhpc_enable_radosgw_usage_exporter | bool %}
+- name: rgws
+  rules:
+  - alert: RadosGWUsageExporterNotServingMetrics
+    expr: absent(radosgw_user_metadata)
+    for: 5m
+    labels:
+      severity: critical
+    annotations:
+      description: "The RadosGW Usage Exporter has not been serving RGW metrics for more than 5 minutes. The exporter may be unable to reach the RGWs."
+{% endif %}

releasenotes/notes/alert-on-radosgw-usage-exporter-8f03f7013204ea22.yaml

@@ -0,0 +1,6 @@
+---
+features:
+  - |
+    Added a new alert ``RadosGWUsageExporterNotServingMetrics``, which will
+    fire when the RadosGW Usage Exporter fails to serve RGW metrics for more
+    than 5 minutes.