alertgroup: "{{ $labels.instance }}"
annotations:
busy_workers: "{{ $value | humanizePercentage }}"
+ - name: chef
+ rules:
+ - alert: chef client not running
+ expr: time() - node_systemd_timer_last_trigger_seconds{name="chef-client.timer"} > 3600
+ for: 12h
+ labels:
+ alertgroup: "{{ $labels.instance }}"
+ annotations:
+ down_time: "{{ $value | humanizeDuration }}"
- name: cpu
rules:
- alert: cpu pressure
- expr: rate(node_pressure_cpu_waiting_seconds_total[5m]) > 0.3
+ expr: rate(node_pressure_cpu_waiting_seconds_total[5m]) > 0.6
for: 15m
labels:
alertgroup: "{{ $labels.instance }}"