prometheus: monitor keepalived

playbooks/prometheus.yml

@@ -3,9 +3,23 @@
 - hosts:
     - pve_network
     - vm_network
+  vars:
+    prometheus_node__text_dir: /var/run/prometheus-node-exporter
   roles:
     - prometheus_node
 
+- hosts:
+    - edge-1.rtr.infra.auro.re
+    - edge-2.rtr.infra.auro.re
+    - isp-1.rtr.infra.auro.re
+    - isp-2.rtr.infra.auro.re
+    - infra-1.rtr.infra.auro.re
+    - infra-2.rtr.infra.auro.re
+  vars:
+    prometheus_keepalived__dest: /var/run/prometheus-node-exporter/keepalived.prom
+  roles:
+    - prometheus_keepalived
+
 - hosts:
     - edge-1.rtr.infra.auro.re
     - edge-2.rtr.infra.auro.re
@@ -214,6 +228,23 @@
             severity: warning
           annotations:
             summary: "{{ '$labels.disk' | interp }}"
+      keepalived:
+        - alert: KeepalivedVrrpFault
+          expr: 'keepalived_vrrp_state{state="fault"} > 0'
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: "{{ '$labels.instance' | interp }}"
+        - alert: KeepalivedMasterChange
+          expr: 'changes(
+                   keepalived_vrrp_state
+                     {keepalived_vvrp_state="master"}[1m]) > 1'
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: "{{ '$labels.instance' | interp }}"
       bird:
         - alert: BirdProtocolDown
           expr: "bird_protocol_up == 0"