diff --git a/files/alerting_rules.yml b/files/alerting_rules.yml index c1178b4..5cf4cde 100644 --- a/files/alerting_rules.yml +++ b/files/alerting_rules.yml @@ -65,6 +65,22 @@ groups: summary: A switch port changed it's state {{ $value }}x time description: "For some reason a switch port changed it's state\n LABELS = {{ $labels }}" + - alert: PortIfInErrors + expr: ifInErrors > 0 + labels: + severity: critical + annotations: + summary: "{{ $labels.ifName }} on {{ $labels.instance }} has {{ $value }} ifInErrors" + description: "For some reason the port is throwing ifInErrors. Clear port counters to clear the alarm" + + - alert: PortIfOutErrors + expr: ifOutErrors > 0 + labels: + severity: critical + annotations: + summary: "{{ $labels.ifName }} on {{ $labels.instance }} has {{ $value }} ifOutErrors" + description: "For some reason the port is throwing ifOutErrors. Clear port counters to clear the alarm" + - alert: SNMPNodeRebooted expr: (sysUpTime / 100) <= (60 * 60 * 2) for: 0m