1 # DO NOT EDIT - This file is being maintained by Chef
7 expr: junos_interface_up{site="amsterdam",name=~"ge-[01]/2/2"} != 1
10 alertgroup: "amsterdam"
12 status: "{{ $value }}"
13 - alert: pdu current draw
14 expr: rPDU2PhaseStatusCurrent{site="amsterdam",rPDU2PhaseStatusIndex="1"} / 10 > 28
17 alertgroup: "amsterdam"
19 current: "{{ $value | humanize }}A"
21 expr: sum(avg_over_time(rPDU2PhaseStatusApparentPower{site="amsterdam",rPDU2PhaseStatusIndex="1"}[1h]) / 100) > 3.5
24 alertgroup: "amsterdam"
26 current: "{{ $value | humanize }}kVA"
27 - alert: site temperature
28 expr: min(rPDU2SensorTempHumidityStatusTempC{site="amsterdam"}) / 10 < 18 or min(rPDU2SensorTempHumidityStatusTempC{site="amsterdam"}) / 10 > 26
31 alertgroup: "amsterdam"
33 temperature: "{{ $value | humanize }}C"
34 - alert: site humidity
35 expr: max(rPDU2SensorTempHumidityStatusRelativeHumidity{site="amsterdam"}) / 100 < 0.25 or max(rPDU2SensorTempHumidityStatusRelativeHumidity{site="amsterdam"}) / 100 > 0.65
38 alertgroup: "amsterdam"
40 humidity: "{{ $value | humanizePercentage }}"
47 alertgroup: "{{ $labels.instance }}"
48 - alert: apache workers busy
49 expr: sum(apache_workers{state="busy"}) by (instance) / sum(apache_scoreboard) by (instance) > 0.8
52 alertgroup: "{{ $labels.instance }}"
54 busy_workers: "{{ $value | humanizePercentage }}"
55 - alert: apache connection limit
56 expr: (apache_connections{state="total"} - on (instance) apache_connections{state="closing"}) / on (instance) (apache_server_limit * on (instance) (apache_threads_per_child + on (instance) (apache_async_request_worker_factor * on (instance) apache_workers{state="idle"} / on(instance) apache_processes{state="all"}))) > 0.8
59 alertgroup: "{{ $labels.instance }}"
61 connections: "{{ $value | humanizePercentage }}"
64 - alert: chef client not running
65 expr: time() - node_systemd_timer_last_trigger_seconds{name="chef-client.timer"} > 3600
68 alertgroup: "{{ $labels.instance }}"
70 down_time: "{{ $value | humanizeDuration }}"
73 - alert: cisco fan alarm
74 expr: rlPhdUnitEnvParamFan1Status{rlPhdUnitEnvParamFan1Status!="normal"} > 0 or rlPhdUnitEnvParamFan2Status{rlPhdUnitEnvParamFan2Status!="normal"} > 0
77 alertgroup: "{{ $labels.site }}"
79 fan_rpm: "{{ with printf \"rlPhdUnitEnvParamFan1Speed{site='%s',instance='%s',rlPhdUnitEnvParamStackUnit='%s'}\" $labels.site $labels.instance $labels.rlPhdUnitEnvParamStackUnit | query }}{{ . | first | value | humanize }}rpm{{end}}"
80 - alert: cisco temperature alarm
81 expr: rlPhdUnitEnvParamTempSensorStatus{rlPhdUnitEnvParamTempSensorStatus!="ok"} > 0
84 alertgroup: "{{ $labels.site }}"
86 temp_celsius: "{{ with printf \"rlPhdUnitEnvParamTempSensorValue{site='%s',instance='%s',rlPhdUnitEnvParamStackUnit='%s'}\" $labels.site $labels.instance $labels.rlPhdUnitEnvParamStackUnit | query }}{{ . | first | value | humanize }}C{{end}}"
87 - alert: cisco main power alarm
88 expr: rlPhdUnitEnvParamMainPSStatus{rlPhdUnitEnvParamMainPSStatus!="normal"} > 0
91 alertgroup: "{{ $labels.site }}"
92 - alert: cisco redundant power alarm
93 expr: rlPhdUnitEnvParamRedundantPSStatus{rlPhdUnitEnvParamRedundantPSStatus!="normal"} > 0
96 alertgroup: "{{ $labels.site }}"
100 expr: rate(node_pressure_cpu_waiting_seconds_total[5m]) > 0.75
103 alertgroup: "{{ $labels.instance }}"
105 pressure: "{{ $value | humanizePercentage }}"
108 - alert: active rails queries
109 expr: sum(pg_stat_activity_count{datname="openstreetmap",usename="rails",state="active"}) by (instance) > 50 and on (instance) chef_role{name="db-master"}
114 queries: "{{ $value }}"
115 - alert: active cgimap queries
116 expr: sum(pg_stat_activity_count{datname="openstreetmap",usename="cgimap",state="active"}) by (instance) > 30 and on (instance) chef_role{name="db-master"}
121 delay: "{{ $value }}"
124 - alert: discourse job failure rate
125 expr: rate(discourse_job_failures[5m]) > 0
128 alertgroup: discourse
130 failure_rate: "{{ $value }} jobs/s"
134 expr: junos_interface_up{site="dublin",name=~"ge-[01]/2/2"} != 1
139 status: "{{ $value }}"
140 - alert: pdu current draw
141 expr: rPDU2PhaseStatusCurrent{site="dublin",rPDU2PhaseStatusIndex="1"} / 10 > 28
146 current: "{{ $value | humanize }}A"
148 expr: sum(avg_over_time(rPDU2PhaseStatusApparentPower{site="dublin",rPDU2PhaseStatusIndex="1"}[1h]) / 100) > 4
153 current: "{{ $value | humanize }}kVA"
154 - alert: site temperature
155 expr: min(rPDU2SensorTempHumidityStatusTempC{site="dublin"}) / 10 < 18 or min(rPDU2SensorTempHumidityStatusTempC{site="dublin"}) / 10 > 26
160 temperature: "{{ $value | humanize }}C"
161 - alert: site humidity
162 expr: max(rPDU2SensorTempHumidityStatusRelativeHumidity{site="dublin"}) / 100 < 0.25 or max(rPDU2SensorTempHumidityStatusRelativeHumidity{site="dublin"}) / 100 > 0.65
167 humidity: "{{ $value | humanizePercentage }}"
170 - alert: fastly error rate
171 expr: sum(rate(fastly_rt_status_group_total{status_group="5xx"}[5m])) by (service_name, datacenter) / sum(rate(fastly_rt_status_group_total[5m])) by (service_name, datacenter) > 0.005
176 error_rate: "{{ $value | humanizePercentage }}"
177 - alert: fastly frontend healthcheck warning
178 expr: count(fastly_healthcheck_status == 0) by (service, datacenter) > 2
182 - alert: fastly frontend healthcheck critical
183 expr: count(fastly_healthcheck_status == 0) by (service, datacenter) == count(fastly_healthcheck_status) by (service, datacenter)
187 - alert: fastly backend healthcheck warning
188 expr: count(fastly_healthcheck_status == 0) by (service, backend) > 10
192 - alert: fastly backend healthcheck critical
193 expr: count(fastly_healthcheck_status == 0) by (service, backend) == count(fastly_healthcheck_status) by (service, backend)
199 - alert: readonly filesystem
200 expr: node_filesystem_readonly > min_over_time(node_filesystem_readonly[7d])
203 alertgroup: "{{ $labels.instance }}"
204 - alert: filesystem low on space
205 expr: node_filesystem_avail_bytes / node_filesystem_size_bytes < 0.05
208 alertgroup: "{{ $labels.instance }}"
210 percentage_free: "{{ $value | humanizePercentage }}"
211 free_bytes: "{{ with printf \"node_filesystem_avail_bytes{instance='%s',mountpoint='%s'}\" $labels.instance $labels.mountpoint | query }}{{ . | first | value | humanize1024 }}bytes{{end}}"
212 total_total: "{{ with printf \"node_filesystem_size_bytes{instance='%s',mountpoint='%s'}\" $labels.instance $labels.mountpoint | query }}{{ . | first | value | humanize1024 }}bytes{{end}}"
213 - alert: filesystem low on inodes
214 expr: node_filesystem_files_free / node_filesystem_files < 0.1
217 alertgroup: "{{ $labels.instance }}"
219 percentage_free: "{{ $value | humanizePercentage }}"
220 free_inodes: "{{ with printf \"node_filesystem_files_free{instance='%s',mountpoint='%s'}\" $labels.instance $labels.mountpoint | query }}{{ . | first | value }}{{end}}"
221 total_inodes: "{{ with printf \"node_filesystem_files{instance='%s',mountpoint='%s'}\" $labels.instance $labels.mountpoint | query }}{{ . | first | value }}{{end}}"
224 - alert: hwmon fan alarm
225 expr: node_hwmon_fan_alarm == 1
228 alertgroup: "{{ $labels.instance }}"
230 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}}"
231 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}}"
232 - alert: hwmon temperature alarm
233 expr: node_hwmon_temp_alarm == 1
236 alertgroup: "{{ $labels.instance }}"
238 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}}"
239 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}}"
240 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}}"
241 - alert: hwmon voltage alarm
242 expr: node_hwmon_in_alarm == 1
245 alertgroup: "{{ $labels.instance }}"
247 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}}"
248 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}}"
249 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}}"
253 expr: rate(node_pressure_io_waiting_seconds_total[5m]) > 0.6
256 alertgroup: "{{ $labels.instance }}"
258 pressure: "{{ $value | humanizePercentage }}"
261 - alert: ipmi fan alarm
262 expr: ipmi_fan_speed_state > 0
265 alertgroup: "{{ $labels.instance }}"
267 fan_speed_rpm: "{{ with printf \"ipmi_fan_speed_rpm{instance='%s',id='%s'}\" $labels.instance $labels.id | query }}{{ . | first | value | humanize }}rpm{{end}}"
268 - alert: ipmi temperature alarm
269 expr: ipmi_temperature_state > 0
272 alertgroup: "{{ $labels.instance }}"
274 temperature_celsius: "{{ with printf \"ipmi_temperature_celsius{instance='%s',id='%s'}\" $labels.instance $labels.id | query }}{{ . | first | value | humanize }}C{{end}}"
275 - alert: ipmi voltage alarm
276 expr: ipmi_voltage_state > 0
279 alertgroup: "{{ $labels.instance }}"
281 voltage_volts: "{{ with printf \"ipmi_voltage_volts{instance='%s',id='%s'}\" $labels.instance $labels.id | query }}{{ . | first | value | humanize }}V{{end}}"
282 - alert: ipmi power alarm
283 expr: ipmi_power_state > 0 or ipmi_sensor_state{type=~"Power .*"} > 0
286 alertgroup: "{{ $labels.instance }}"
289 - alert: juniper red alarms
290 expr: juniper_alarms_red_count > 0
293 alertgroup: "{{ $labels.site }}"
295 alarm_count: "{{ $value }} alarms"
296 - alert: juniper yellow alarms
297 expr: juniper_alarms_yellow_count > 0
300 alertgroup: "{{ $labels.site }}"
302 alarm_count: "{{ $value }} alarms"
303 - alert: juniper cpu alarm
304 expr: junos_route_engine_load_average_five / 2 > 0.5
307 alertgroup: "{{ $labels.site }}"
309 load_average: "{{ $value | humanizePercentage }}"
310 - alert: juniper fan alarm
311 expr: junos_environment_fan_up != 1
314 alertgroup: "{{ $labels.site }}"
315 - alert: juniper power alarm
316 expr: junos_environment_power_up != 1
319 alertgroup: "{{ $labels.site }}"
320 - alert: juniper laser receive power
321 expr: junos_interface_diagnostics_laser_rx_dbm < -12 and on (site, instance, name) junos_interface_admin_up == 1
324 alertgroup: "{{ $labels.site }}"
326 power: "{{ $value }} dBm"
327 - alert: juniper laser transmit power
328 expr: junos_interface_diagnostics_laser_output_dbm < -8 and on (site, instance, name) junos_interface_admin_up == 1
331 alertgroup: "{{ $labels.site }}"
333 power: "{{ $value }} dBm"
340 alertgroup: "{{ $labels.instance }}"
341 - alert: exim queue length
342 expr: exim_queue > ignoring(job) exim_queue_limit
347 queue_length: "{{ $value }}"
348 - alert: mailman queue length
349 expr: mailman_queue_length > 200
354 queue_length: "{{ $value }}"
357 - alert: mdadm array inactive
358 expr: node_md_state{state="inactive"} > 0
361 alertgroup: "{{ $labels.instance }}"
363 required: "{{ with printf \"node_md_disks_required{instance='%s',device='%s'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
364 active: "{{ with printf \"node_md_disks{instance='%s',device='%s',state='active'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
365 failed: "{{ with printf \"node_md_disks{instance='%s',device='%s',state='failed'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
366 spare: "{{ with printf \"node_md_disks{instance='%s',device='%s',state='spare'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
367 - alert: mdadm array degraded
368 expr: sum (node_md_disks{state="active"}) without (state) < node_md_disks_required
371 alertgroup: "{{ $labels.instance }}"
373 required: "{{ with printf \"node_md_disks_required{instance='%s',device='%s'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
374 active: "{{ with printf \"node_md_disks{instance='%s',device='%s',state='active'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
375 failed: "{{ with printf \"node_md_disks{instance='%s',device='%s',state='failed'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
376 spare: "{{ with printf \"node_md_disks{instance='%s',device='%s',state='spare'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
377 - alert: mdadm disk failed
378 expr: node_md_disks{state="failed"} > 0
381 alertgroup: "{{ $labels.instance }}"
383 required: "{{ with printf \"node_md_disks_required{instance='%s',device='%s'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
384 active: "{{ with printf \"node_md_disks{instance='%s',device='%s',state='active'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
385 failed: "{{ with printf \"node_md_disks{instance='%s',device='%s',state='failed'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
386 spare: "{{ with printf \"node_md_disks{instance='%s',device='%s',state='spare'}\" $labels.instance $labels.device | query }}{{ . | first | value | humanize }} disks{{end}}"
390 expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes < 0.1
393 alertgroup: "{{ $labels.instance }}"
395 memory_free: "{{ $value | humanizePercentage }}"
396 - alert: memory pressure
397 expr: rate(node_pressure_memory_waiting_seconds_total[5m]) > 0.6
400 alertgroup: "{{ $labels.instance }}"
402 pressure: "{{ $value | humanizePercentage }}"
403 - alert: oom kill detected
404 expr: increase(node_vmstat_oom_kill[1m]) > 0
407 alertgroup: "{{ $labels.instance }}"
409 new_oom_kills: "{{ $value }}"
416 alertgroup: "{{ $labels.instance }}"
417 - alert: mysql connection limit
418 expr: mysql_global_status_max_used_connections / mysql_global_variables_max_connections > 0.8
421 alertgroup: "{{ $labels.instance }}"
423 connections_used: "{{ $value | humanizePercentage }}"
424 - alert: mysql connection errors
425 expr: increase(mysql_global_status_connection_errors_total[1m]) > 0
428 alertgroup: "{{ $labels.instance }}"
430 error_count: "{{ $value }}"
433 - alert: interface redundancy lost
434 expr: node_bonding_active < 2 and on (instance, master) label_replace(chef_network_interface{bond_mode="802.3ad"}, "master", "$1", "name", "(.*)")
437 alertgroup: "{{ $labels.instance }}"
439 link_count: "{{ $value }}"
440 - alert: interface transmit rate
441 expr: rate(node_network_transmit_bytes_total[1m]) / node_network_speed_bytes > 0.99
444 alertgroup: "{{ $labels.instance }}"
446 bandwidth_used: "{{ $value | humanizePercentage }}"
447 - alert: interface receive rate
448 expr: rate(node_network_receive_bytes_total[1m]) / node_network_speed_bytes > 0.99
451 alertgroup: "{{ $labels.instance }}"
453 bandwidth_used: "{{ $value | humanizePercentage }}"
454 - alert: interface transmit errors
455 expr: rate(node_network_transmit_errs_total{device!~"wg.*"}[1m]) / rate(node_network_transmit_packets_total{device!~"wg.*"}[1m]) > 0.01
458 alertgroup: "{{ $labels.instance }}"
460 error_rate: "{{ $value | humanizePercentage }}"
461 - alert: wireguard interface transmit errors
462 expr: rate(node_network_transmit_errs_total{device=~"wg.*"}[1m]) / rate(node_network_transmit_packets_total{device=~"wg.*"}[1m]) > 0.05
465 alertgroup: "{{ $labels.instance }}"
467 error_rate: "{{ $value | humanizePercentage }}"
468 - alert: interface receive errors
469 expr: rate(node_network_receive_errs_total[1m]) / rate(node_network_receive_packets_total[1m]) > 0.01
472 alertgroup: "{{ $labels.instance }}"
474 error_rate: "{{ $value | humanizePercentage }}"
475 - alert: conntrack entries
476 expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8
479 alertgroup: "{{ $labels.instance }}"
481 entries_used: "{{ $value | humanizePercentage }}"
484 - alert: nominatim replication delay
485 expr: nominatim_replication_delay > 10800
488 alertgroup: nominatim
490 delay: "{{ $value | humanizeDuration }}"
493 - alert: overpass osm database age
494 expr: overpass_database_age_seconds{database="osm"} > 3600
499 age: "{{ $value | humanizeDuration }}"
500 - alert: overpass area database age
501 expr: overpass_database_age_seconds{database="area"} > 86400
506 age: "{{ $value | humanizeDuration }}"
509 - alert: passenger down
510 expr: passenger_up == 0
513 alertgroup: "{{ $labels.instance }}"
514 - alert: passenger queuing
515 expr: passenger_top_level_request_queue > 0
518 alertgroup: "{{ $labels.instance }}"
519 - alert: passenger application queuing
520 expr: passenger_app_request_queue > 0
523 alertgroup: "{{ $labels.instance }}"
526 - alert: planet dump overdue
527 expr: time() - file_stat_modif_time_seconds{path=~"/store/planet/(pbf|planet)/.*"} > 7 * 86400 and ignoring (job, name, path) chef_role{name="planetdump"} == 1
532 overdue_by: "{{ $value | humanizeDuration }}"
533 - alert: notes dump overdue
534 expr: time() - file_stat_modif_time_seconds{path=~"/store/planet/notes/.*"} > 86400 and ignoring (job, name, path) chef_role{name="planetdump"} == 1
539 overdue_by: "{{ $value | humanizeDuration }}"
540 - alert: daily replication feed delayed
541 expr: time() - file_stat_modif_time_seconds{path=~"/store/planet/replication/day/.*"} > 86400 and ignoring (job, name, path) chef_role{name="planetdump"} == 1
546 delayed_by: "{{ $value | humanizeDuration }}"
547 - alert: hourly replication feed delayed
548 expr: time() - file_stat_modif_time_seconds{path=~"/store/planet/replication/hour/.*"} > 3600 and ignoring (job, name, path) chef_role{name="planetdump"} == 1
553 delayed_by: "{{ $value | humanizeDuration }}"
554 - alert: minutely replication feed delayed
555 expr: time() - file_stat_modif_time_seconds{path=~"/store/planet/replication/minute/.*"} > 60 and ignoring (job, name, path) chef_role{name="planetdump"} == 1
560 delayed_by: "{{ $value | humanizeDuration }}"
561 - alert: changeset replication feed delayed
562 expr: time() - file_stat_modif_time_seconds{path=~"/store/planet/replication/changesets/.*"} > 60 and ignoring (job, name, path) chef_role{name="planetdump"} == 1
567 delayed_by: "{{ $value | humanizeDuration }}"
570 - alert: postgresql down
574 alertgroup: "{{ $labels.instance }}"
575 - alert: postgresql replication delay
576 expr: pg_replication_lag_seconds > 30
579 alertgroup: "{{ $labels.instance }}"
581 delay: "{{ $value | humanizeDuration }}"
582 - alert: postgresql connection limit
583 expr: sum (pg_stat_activity_count) by (instance, server) / sum (pg_settings_max_connections) by (instance, server) > 0.8
586 alertgroup: "{{ $labels.instance }}"
588 connections_used: "{{ $value | humanizePercentage }}"
589 - alert: postgresql deadlocks
590 expr: increase(pg_stat_database_deadlocks{datname!="nominatim"}[1m]) > 5
593 alertgroup: "{{ $labels.instance }}"
595 new_deadlocks: "{{ $value }}"
596 - alert: postgresql idle transactions
597 expr: sum(pg_process_idle_seconds_count{state="idle in transaction"}) by (instance, server) > sum(pg_process_idle_seconds_bucket{state="idle in transaction",le="300"}) by (instance, server)
600 alertgroup: "{{ $labels.instance }}"
602 queries: "{{ $value }}"
605 - alert: prometheus configuration error
606 expr: prometheus_config_last_reload_successful == 0
609 alertgroup: "prometheus"
610 - alert: prometheus target missing
614 alertgroup: "prometheus"
617 - alert: raid controller battery failed
618 expr: ohai_controller_info{battery_status="failed"} > 0
621 alertgroup: "{{ $labels.instance }}"
622 - alert: raid controller battery recharging
623 expr: ohai_controller_info{battery_status="recharging"} > 0
626 alertgroup: "{{ $labels.instance }}"
627 - alert: raid array degraded
628 expr: ohai_array_info{status="degraded"} > 0
631 alertgroup: "{{ $labels.instance }}"
632 - alert: raid disk failed
633 expr: ohai_disk_info{status="failed"} > 0
636 alertgroup: "{{ $labels.instance }}"
639 - alert: memory controller errors
640 expr: increase(rasdaemon_mc_events_total[1m]) > 0
643 alertgroup: "{{ $labels.instance }}"
645 new_errors: "{{ $value }}"
646 - alert: pcie aer errors
647 expr: increase(rasdaemon_aer_events_total[1m]) > 0
650 alertgroup: "{{ $labels.instance }}"
652 new_errors: "{{ $value }}"
655 - alert: smart failure
656 expr: smart_health_status == 0
659 alertgroup: "{{ $labels.instance }}"
660 - alert: smart ssd wearout approaching
661 expr: smart_percentage_used / 100 >= 0.8
664 alertgroup: "{{ $labels.instance }}"
666 percentage_used: "{{ $value | humanizePercentage }}"
670 expr: 1 - (rate(smokeping_response_duration_seconds_count[5m]) / rate(smokeping_requests_total[5m])) > 0.02
673 alertgroup: smokeping
675 loss_rate: "{{ $value | humanizePercentage }}"
678 - alert: snmp pdus missing
679 expr: max_over_time(snmp_scrape_pdus_returned[1d]) - snmp_scrape_pdus_returned > 0
684 missing_pdus: "{{ $value }}"
687 - alert: ssl certificate probe failed
688 expr: ssl_probe_success == 0
692 - alert: ssl certificate expiry
693 expr: ssl_verified_cert_not_after{chain_no="0"} - time() < 86400 * 14
698 expires_in: "{{ $value | humanizeDuration }}"
699 - alert: ssl certificate revoked
700 expr: ssl_ocsp_response_status == 1
704 - alert: ocsp status unknown
705 expr: ssl_ocsp_response_status == 1
711 - alert: statuscake uptime check failing
712 expr: statuscake_paused == 0 and statuscake_up == 0
715 alertgroup: statuscake
718 - alert: systemd failed service
719 expr: node_systemd_unit_state{state="failed",name!="chef-client.service"} == 1
722 alertgroup: "{{ $labels.instance }}"
723 - alert: systemd failed chef client service
724 expr: sum_over_time(node_systemd_unit_state{state="inactive",name="chef-client.service"}[6h]) == 0
727 alertgroup: "{{ $labels.instance }}"
730 - alert: taginfo planet age
731 expr: time() - taginfo_data_from_seconds > 129600 and on (instance) chef_role{name="taginfo"}
736 age: "{{ $value | humanizeDuration }}"
737 - alert: taginfo database age
738 expr: time() - taginfo_database_update_finish_seconds > 129600 and on (instance) chef_role{name="taginfo"}
743 age: "{{ $value | humanizeDuration }}"
744 - alert: taginfo database size
745 expr: abs(delta(taginfo_database_size_bytes[30m])) / taginfo_database_size_bytes > 0.1
750 size_change: "{{ $value | humanizePercentage }}"
753 - alert: renderd replication delay
754 expr: renderd_replication_delay > 120
759 delay: "{{ $value | humanizeDuration }}"
760 - alert: missed tile rate
761 expr: sum(rate(modtile_http_response_total{code="404"}[5m])) by (instance) / sum(rate(modtile_http_response_total[5m])) by (instance) > 0.05
766 miss_rate: "{{ $value | humanizePercentage }}"
767 - alert: tile render rate
768 expr: sum(rate(renderd_zoom_metatiles_total[5m])) by (instance) == 0
773 render_rate: "{{ $value }} tiles/s"
776 - alert: clock not synchronising
777 expr: min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16
780 alertgroup: "{{ $labels.instance }}"
781 - alert: clock skew detected
782 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)
785 alertgroup: "{{ $labels.instance }}"
787 skew: "{{ with printf \"node_timex_offset_seconds{instance='%s'}\" $labels.instance | query }} {{ . | humanizeDuration }}{{ end }}"
790 - alert: web error rate
791 expr: sum(rate(api_call_count_total{status=~"50[0-8]|5[1-9][0-9]"}[5m])) by (instance) / sum(rate(api_call_count_total[5m])) by (instance) > 0.002
796 error_rate: "{{ $value | humanizePercentage }}"
797 - alert: job processing rate
798 expr: rate(pg_stat_user_tables_n_tup_del{datname="openstreetmap",relname="delayed_jobs"}[1h]) / rate(pg_stat_user_tables_n_tup_ins{datname="openstreetmap",relname="delayed_jobs"}[1h]) < 0.9 and ignoring(job, name, datname, relname, schemaname, server) chef_role{name="db-master"} == 1
803 job_processing_rate: "{{ $value | humanizePercentage }}"