alertgroup: database
annotations:
delay: "{{ $value | humanizeDuration }}"
+ - name: dublin
+ rules:
+ - alert: pdu current draw
+ expr: rPDU2PhaseStatusCurrent{site="dublin",rPDU2PhaseStatusIndex="1"} / 10 > 13
+ for: 5m
+ labels:
+ alertgroup: "dublin"
+ annotations:
+ current: "{{ $value | humanize }}A"
+ - alert: site current draw
+ expr: sum(rPDU2PhaseStatusCurrent{site="dublin",rPDU2PhaseStatusIndex="1"} / 10) > 17
+ for: 5m
+ 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
+ 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
+ labels:
+ alertgroup: "dublin"
+ annotations:
+ humidity: "{{ $value | humanizePercentage }}"
- name: fastly
rules:
- alert: fastly error rate
for: 15m
labels:
alertgroup: fastly
- - alert: fastly healthcheck failing
+ - alert: multiple fastly healthchecks failing
expr: count(fastly_healthcheck_status == 0) > 4
for: 5m
labels:
- name: juniper
rules:
- alert: juniper fan alarm
- expr: jnxOperatingState{jnxOperatingContentsIndex="4",jnxOperatingState!="running"} > 0
+ expr: sum_over_time(jnxOperatingState{jnxOperatingContentsIndex="4",jnxOperatingState!="running"}[6m]) > 0
for: 5m
labels:
alertgroup: "{{ $labels.site }}"
- alert: juniper power alarm
- expr: jnxOperatingState{jnxOperatingContentsIndex="2",jnxOperatingState!="running"} > 0
+ expr: sum_over_time(jnxOperatingState{jnxOperatingContentsIndex="2",jnxOperatingState!="running"}[6m]) > 0
for: 5m
labels:
alertgroup: "{{ $labels.site }}"
alertgroup: "{{ $labels.instance }}"
annotations:
error_rate: "{{ $value | humanizePercentage }}"
- - alert: interface transmit errors
+ - alert: wireguard interface transmit errors
expr: rate(node_network_transmit_errs_total{device=~"wg.*"}[1m]) / rate(node_network_transmit_packets_total{device=~"wg.*"}[1m]) > 0.05
for: 1h
labels:
alertgroup: "{{ $labels.instance }}"
annotations:
entries_used: "{{ $value | humanizePercentage }}"
+ - name: nominatim
+ rules:
+ - alert: nominatim replication delay
+ expr: nominatim_replication_delay > 10800
+ for: 1h
+ labels:
+ alertgroup: nominatim
+ annotations:
+ delay: "{{ $value | humanizeDuration }}"
- name: overpass
rules:
- alert: overpass osm database age
- expr: overpass_database_age_seconds{database="osm"} > 5m
- for: 5m
+ expr: overpass_database_age_seconds{database="osm"} > 3600
+ for: 1h
labels:
alertgroup: overpass
annotations:
age: "{{ $value | humanizeDuration }}"
- alert: overpass area database age
- expr: overpass_database_age_seconds{database="area"} > 24h
+ expr: overpass_database_age_seconds{database="area"} > 86400
for: 1h
labels:
alertgroup: overpass
for: 5m
labels:
alertgroup: "{{ $labels.instance }}"
- - alert: systemd failed service
+ - alert: systemd failed chef client service
expr: node_systemd_unit_state{state="failed",name="chef-client.service"} == 1
for: 6h
labels: