monitoring: add alarm "PublicWifiUpstreamLost"

2022-10-19 02:05:32 +02:00 · 2022-10-19 02:05:32 +02:00 · ec917a24c6
parent df6a5a93ef
commit ec917a24c6
1 changed files with 9 additions and 0 deletions
--- a/files/alerting_rules.yml
+++ b/files/alerting_rules.yml
@ -19,3 +19,12 @@ groups:
          annotations:
            summary: A node rebooted in the last 2 hours (instance {{ $labels.instance }})
            description: "The uptime of a node changed in the last two hours. VALUE = {{ $value }}\n LABELS = {{ $labels }}"
+
+        - alert: PublicWifiUpstreamLost
+          expr: sum(probe_success{job="e2e_clients_v4"}) == 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: The public wifi lost its ability to route into the internet
+            description: "check the vpn connection"