1 # DO NOT EDIT - This file is being maintained by Chef
6 - alert: prometheus target missing
10 alertgroup: "prometheus"
13 - alert: postgres replication delay
14 expr: pg_replication_lag_seconds > 5
19 delay: "{{ $value | humanizeDuration }}"
22 - alert: hwmon fan alarm
23 expr: node_hwmon_fan_alarm == 1
26 alertgroup: "{{ $labels.instance }}"
28 fan_rpm: "{{ with printf \"node_hwmon_fan_rpm{instance='%s',chip='%s',sensor='%s'}\" $labels.instance $labels.chip $labels.sensor | query }}{{ . | first | value | humanize }}rpm{{end}}"
29 fan_min_rpm: "{{ with printf \"node_hwmon_fan_min_rpm{instance='%s',chip='%s',sensor='%s'}\" $labels.instance $labels.chip $labels.sensor | query }}{{ . | first | value | humanize }}rpm{{end}}"
30 - alert: hwmon temperature alarm
31 expr: node_hwmon_temp_alarm == 1
34 alertgroup: "{{ $labels.instance }}"
36 temp_celsius: "{{ with printf \"node_hwmon_temp_celsius{instance='%s',chip='%s',sensor='%s'}\" $labels.instance $labels.chip $labels.sensor | query }}{{ . | first | value | humanize }}C{{end}}"
37 temp_max_celsius: "{{ with printf \"node_hwmon_temp_max_celsius{instance='%s',chip='%s',sensor='%s'}\" $labels.instance $labels.chip $labels.sensor | query }}{{ . | first | value | humanize }}C{{end}}"
38 temp_crit_celsius: "{{ with printf \"node_hwmon_temp_crit_celsius{instance='%s',chip='%s',sensor='%s'}\" $labels.instance $labels.chip $labels.sensor | query }}{{ . | first | value | humanize }}C{{end}}"
39 - alert: hwmon voltage alarm
40 expr: node_hwmon_in_alarm == 1
43 alertgroup: "{{ $labels.instance }}"
45 in_volts: "{{ with printf \"node_hwmon_in_volts{instance='%s',chip='%s',sensor='%s'}\" $labels.instance $labels.chip $labels.sensor | query }}{{ . | first | value | humanize }}V{{end}}"
46 in_min_volts: "{{ with printf \"node_hwmon_in_min_volts{instance='%s',chip='%s',sensor='%s'}\" $labels.instance $labels.chip $labels.sensor | query }}{{ . | first | value | humanize }}V{{end}}"
47 in_max_volts: "{{ with printf \"node_hwmon_in_max_volts{instance='%s',chip='%s',sensor='%s'}\" $labels.instance $labels.chip $labels.sensor | query }}{{ . | first | value | humanize }}V{{end}}"
50 - alert: ipmi fan alarm
51 expr: ipmi_fan_speed_state > 0
54 alertgroup: "{{ $labels.instance }}"
56 fan_speed_rpm: "{{ with printf \"ipmi_fan_speed_rpm{instance='%s',id='%s'}\" $labels.instance $labels.id | query }}{{ . | first | value | humanize }}rpm{{end}}"
57 - alert: ipmi temperature alarm
58 expr: ipmi_temperature_state > 0
61 alertgroup: "{{ $labels.instance }}"
63 temperature_celsius: "{{ with printf \"ipmi_temperature_celsius{instance='%s',id='%s'}\" $labels.instance $labels.id | query }}{{ . | first | value | humanize }}C{{end}}"
64 - alert: ipmi voltage alarm
65 expr: ipmi_voltage_state > 0
68 alertgroup: "{{ $labels.instance }}"
70 voltage_volts: "{{ with printf \"ipmi_voltage_volts{instance='%s',id='%s'}\" $labels.instance $labels.id | query }}{{ . | first | value | humanize }}V{{end}}"
73 - alert: mdadm array inactive
74 expr: node_md_state{state="inactive"} > 0
77 alertgroup: "{{ $labels.instance }}"
79 required: "{{ with printf \"node_md_disks_required{instance='%s',device='%s'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
80 active: "{{ with printf \"node_md_disks{instance='%s',device='%s',state='active'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
81 failed: "{{ with printf \"node_md_disks{instance='%s',device='%s',state='failed'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
82 spare: "{{ with printf \"node_md_disks{instance='%s',device='%s',state='spare'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
83 - alert: mdadm disk failed
84 expr: node_md_disks{state="failed"} > 0
87 alertgroup: "{{ $labels.instance }}"
89 required: "{{ with printf \"node_md_disks_required{instance='%s',device='%s'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
90 active: "{{ with printf \"node_md_disks{instance='%s',device='%s',state='active'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
91 failed: "{{ with printf \"node_md_disks{instance='%s',device='%s',state='failed'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
92 spare: "{{ with printf \"node_md_disks{instance='%s',device='%s',state='spare'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
96 expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes < 0.1
99 alertgroup: "{{ $labels.instance }}"
101 memory_free: "{{ $value | humanizePercentage }}"
102 - alert: memory pressure
103 expr: rate(node_vmstat_pgmajfault[1m]) > 1000
106 alertgroup: "{{ $labels.instance }}"
108 major_page_faults: "{{ $value }} faults/s"
109 - alert: oom kill detected
110 expr: increase(node_vmstat_oom_kill[1m]) > 0
113 alertgroup: "{{ $labels.instance }}"
115 new_oom_kills: "{{ $value }}"
118 - alert: renderd replication delay
119 expr: renderd_replication_delay > 120
124 delay: "{{ $value | humanizeDuration }}"
125 - alert: missed tile rate
126 expr: sum(rate(modtile_http_response_total{code="404"}[5m])) by (instance) / sum(rate(modtile_http_response_total[5m])) by (instance) > 0.05
131 miss_rate: "{{ $value | humanizePercentage }}"
134 - alert: clock not synchronising
135 expr: min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16
138 alertgroup: "{{ $labels.instance }}"
139 - alert: clock skew detected
140 expr: (node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) or (node_timex_offset_seconds < -0.05 and deriv(node_timex_offset_seconds[5m]) <= 0)
143 alertgroup: "{{ $labels.instance }}"
145 skew: "{{ with printf \"node_timex_offset_seconds{instance='%s'}\" $labels.instance | query }} {{ . | humanizeDuration }}{{ end }}"