rules:
- alert: pdu current draw
expr: rPDU2PhaseStatusCurrent{site="amsterdam",rPDU2PhaseStatusIndex="1"} / 10 > 10
- for: 5m
+ for: 6m
labels:
alertgroup: "amsterdam"
annotations:
current: "{{ $value | humanize }}A"
- alert: site current draw
expr: sum(rPDU2PhaseStatusCurrent{site="amsterdam",rPDU2PhaseStatusIndex="1"} / 10) > 13
- for: 5m
+ for: 6m
labels:
alertgroup: "amsterdam"
annotations:
current: "{{ $value | humanize }}A"
- alert: site temperature
- expr: min(rPDU2SensorTempHumidityStatusTempC{site="amsterdam"}) / 10 < 18 or min(rPDU2SensorTempHumidityStatusTempC{site="amsterdam"}) / 10 > 25
- for: 5m
+ expr: min(rPDU2SensorTempHumidityStatusTempC{site="amsterdam"}) / 10 < 18 or min(rPDU2SensorTempHumidityStatusTempC{site="amsterdam"}) / 10 > 25.5
+ for: 6m
labels:
alertgroup: "amsterdam"
annotations:
temperature: "{{ $value | humanize }}C"
- alert: site humidity
expr: max(rPDU2SensorTempHumidityStatusRelativeHumidity{site="amsterdam"}) / 100 < 0.25 or max(rPDU2SensorTempHumidityStatusRelativeHumidity{site="amsterdam"}) / 100 > 0.65
- for: 5m
+ for: 6m
labels:
alertgroup: "amsterdam"
annotations:
rules:
- alert: pdu current draw
expr: rPDU2PhaseStatusCurrent{site="dublin",rPDU2PhaseStatusIndex="1"} / 10 > 13
- for: 5m
+ for: 6m
labels:
alertgroup: "dublin"
annotations:
current: "{{ $value | humanize }}A"
- alert: site current draw
expr: sum(rPDU2PhaseStatusCurrent{site="dublin",rPDU2PhaseStatusIndex="1"} / 10) > 17
- for: 5m
+ for: 6m
labels:
alertgroup: "dublin"
annotations:
current: "{{ $value | humanize }}A"
- alert: site temperature
- expr: min(rPDU2SensorTempHumidityStatusTempC{site="dublin"}) / 10 < 18 or min(rPDU2SensorTempHumidityStatusTempC{site="dublin"}) / 10 > 25
- for: 5m
+ expr: min(rPDU2SensorTempHumidityStatusTempC{site="dublin"}) / 10 < 18 or min(rPDU2SensorTempHumidityStatusTempC{site="dublin"}) / 10 > 25.5
+ for: 6m
labels:
alertgroup: "dublin"
annotations:
temperature: "{{ $value | humanize }}C"
- alert: site humidity
expr: max(rPDU2SensorTempHumidityStatusRelativeHumidity{site="dublin"}) / 100 < 0.25 or max(rPDU2SensorTempHumidityStatusRelativeHumidity{site="dublin"}) / 100 > 0.65
- for: 5m
+ for: 6m
labels:
alertgroup: "dublin"
annotations:
- name: filesystem
rules:
- alert: readonly filesystem
- expr: node_filesystem_readonly == 1
+ expr: node_filesystem_readonly > min_over_time(node_filesystem_readonly[7d])
for: 0m
labels:
alertgroup: "{{ $labels.instance }}"
alertgroup: "{{ $labels.instance }}"
- name: juniper
rules:
+ - alert: juniper cpu alarm
+ expr: jnxOperatingCPU{jnxOperatingContentsIndex="7"} > 30
+ for: 5m
+ labels:
+ alertgroup: "{{ $labels.site }}"
- alert: juniper fan alarm
- expr: sum_over_time(jnxOperatingState{jnxOperatingContentsIndex="4",jnxOperatingState!~"running.*"}[6m]) > 0
+ expr: jnxOperatingState{jnxOperatingContentsIndex="4",jnxOperatingState!~"running.*"} > 0
for: 5m
labels:
alertgroup: "{{ $labels.site }}"
- alert: juniper power alarm
- expr: sum_over_time(jnxOperatingState{jnxOperatingContentsIndex="2",jnxOperatingState!~"running.*"}[6m]) > 0
+ expr: jnxOperatingState{jnxOperatingContentsIndex="2",jnxOperatingState!~"running.*"} > 0
for: 5m
labels:
alertgroup: "{{ $labels.site }}"
- name: mail
rules:
+ - alert: exim down
+ expr: exim_up == 0
+ for: 5m
+ labels:
+ alertgroup: "{{ $labels.instance }}"
- alert: exim queue length
expr: exim_queue > exim_queue_limit
for: 60m
alertgroup: overpass
annotations:
age: "{{ $value | humanizeDuration }}"
+ - name: passenger
+ rules:
+ - alert: passenger down
+ expr: passenger_up == 0
+ for: 5m
+ labels:
+ alertgroup: "{{ $labels.instance }}"
+ - alert: passenger queuing
+ expr: passenger_top_level_request_queue > 0
+ for: 5m
+ labels:
+ alertgroup: "{{ $labels.instance }}"
+ - alert: passenger application queuing
+ expr: passenger_app_request_queue > 0
+ for: 5m
+ labels:
+ alertgroup: "{{ $labels.instance }}"
- name: planet
rules:
- alert: planet dump overdue