1
0
Fork 0
kubernetes/victoria-metrics/alerts.yml

110 lines
3.3 KiB
YAML

groups:
- name: default alert
rules:
- alert: DiskUsage
expr: >-
sum(collectd_df_df_complex{type!="free"}) by (instance, df) / sum(collectd_df_df_complex{df!="var-log", df!="var-lib-frigate"}) by (instance, df) > .75
or sum(collectd_df_df_complex{type!="free"}) by (instance, df) / sum(collectd_df_df_complex{df="var-log"}) by (instance, df) > .95
or sum(collectd_df_df_complex{type!="free"}) by (instance, df) / sum(collectd_df_df_complex{df="var-lib-frigate"}) by (instance, df) > .95
for: 2h
- alert: TheWebsiteIsDown
expr: >-
probe_success{job="websites"} == 0
for: 10m
- alert: Missing Metrics
expr: >-
up{instance!~"vmhost.*"} == 0
for: 10m
- alert: NUT is offline
expr: >-
absent(collectd_nut_percent)
for: 10m
- name: Bitwarden
rules:
- alert: vaultwarden is not running
expr: >-
collectd_processes_ps_count_processes{processes="vaultwarden"} < 1
for: 5m
- name: Active Directory
rules:
- alert: samba is not running
expr: >-
collectd_processes_ps_count_processes{processes=~"samba|smbd|winbindd|krb5kdc"} < 1
for: 5m
- name: mdraid
rules:
- alert: mdraid missing disk
expr: collectd_md_md_disks{type="missing", instance!~"burp.*"} != 0
- alert: mdraid failed disk
expr: collectd_md_md_disks{type="failed"} != 0
- name: certificates
rules:
- alert: certificate will expire soon
expr:
probe_ssl_last_chain_expiry_timestamp_seconds - time() < 29 * 86400
annotations:
summary: A certificate will expire in less than 29 days
description: >-
Generally, certificates are renewed automatically, approximately 30
days before their expiration (NotAfter) date. There may be a problem
with the certificate renewal process that prevented this certificate
from being renewed.
- alert: certificate will expire very soon
expr:
probe_ssl_last_chain_expiry_timestamp_seconds - time() < 14 * 86400
annotations:
summary: A certificate will expire in less than 14 days
description: >-
Generally, certificates are renewed automatically, approximately 30
days before their expiration (NotAfter) date. There is most likely a
problem with the certificate renewal process that prevented this
certificate from being renewed.
- name: Frigate
rules:
- alert: Frigate is Unavailable
expr:
homeassistant_entity_available{entity=~".*frigate_(server|status)"} != 1
for: 10m
- alert: Camera unavailable
expr:
homeassistant_entity_available{domain="camera"} != 1
for: 10m
- name: Sensors
rules:
- alert: Battery Low
expr:
homeassistant_sensor_battery_percent{entity!~"sensor\\.(pixel_|sm_p610).*"} < 10
- name: PostgreSQL
rules:
- alert: Replica lag too high
expr:
(patroni_xlog_location != 0)
- ignoring (instance) group_right (scope) (patroni_xlog_replayed_location != 0)
> 10240
for: 10m
- name: Temperature
rules:
- alert: High Temperature
expr: >-
{__name__=~"collectd_.*_temperature", sensors!~"i350bb.*"} > 80
for: 10m
- name: Longhorn
rules:
- alert: Degraded Volumes
expr: >-
count(longhorn_volume_robustness==2) > 0
for: 1h
- alert: Faulted Volumes
expr: >-
count(longhorn_volume_robustness==3) > 0
for: 5m