alertgroup: "{{ $labels.instance }}"
- name: juniper
rules:
+ - alert: juniper red alarms
+ expr: juniper_alarms_red_count > 0
+ for: 5m
+ labels:
+ alertgroup: "{{ $labels.site }}"
+ annotations:
+ alarm_count: "{{ $value }} alarms"
+ - alert: juniper yellow alarms
+ expr: juniper_alarms_yellow_count > 0
+ for: 5m
+ labels:
+ alertgroup: "{{ $labels.site }}"
+ annotations:
+ alarm_count: "{{ $value }} alarms"
- alert: juniper cpu alarm
- expr: junos_route_engine_load_average_five > 0.5
+ expr: junos_route_engine_load_average_five / 2 > 0.5
for: 5m
labels:
alertgroup: "{{ $labels.site }}"
annotations:
load_average: "{{ $value | humanizePercentage }}"
- alert: juniper fan alarm
- expr: jnxOperatingState{jnxOperatingContentsIndex="4",jnxOperatingState!~"running.*"} > 0
+ expr: junos_environment_fan_up != 1
for: 5m
labels:
alertgroup: "{{ $labels.site }}"
- name: taginfo
rules:
- alert: taginfo planet age
- expr: time() - taginfo_data_from_seconds > 129600
+ expr: time() - taginfo_data_from_seconds > 129600 and on (instance) chef_role{name="taginfo"}
for: 0m
labels:
alertgroup: taginfo
annotations:
age: "{{ $value | humanizeDuration }}"
- alert: taginfo database age
- expr: time() - taginfo_database_update_finish_seconds > 129600
+ expr: time() - taginfo_database_update_finish_seconds > 129600 and on (instance) chef_role{name="taginfo"}
for: 0m
labels:
alertgroup: taginfo