monitoring: alert on snmp if{In,Out}Errors
This commit is contained in:
parent
14df3e24df
commit
d1c1f34bf8
|
@ -65,6 +65,22 @@ groups:
|
||||||
summary: A switch port changed it's state {{ $value }}x time
|
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 }}"
|
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
|
- alert: SNMPNodeRebooted
|
||||||
expr: (sysUpTime / 100) <= (60 * 60 * 2)
|
expr: (sysUpTime / 100) <= (60 * 60 * 2)
|
||||||
for: 0m
|
for: 0m
|
||||||
|
|
Loading…
Reference in New Issue