traefik

alert: TraefikConfigReloadFailuresIncreasing
annotations:
  description: |
    Traefik is failing to reload its config in {{ $labels.job }}.
  summary: Traefik is failing to reload its configuration.
expr: |
  sum by (job) (rate(traefik_config_reloads_failure_total{}[5m])) > 0
for: 5m
labels:
  severity: critical

alert: TraefikTLSCertificatesExpiring
annotations:
  description: |
    The minimum number of days until a Traefik-served certificate expires is {{ printf "%.0f" $value }} days on {{ $labels.sans }} which is below the critical threshold of 7.
  summary: A Traefik-served TLS certificate will expire very soon.
expr: |
  max by (instance, sans) ((last_over_time(traefik_tls_certs_not_after{}[5m]) - time()) / 86400) < 7
for: 5m
labels:
  severity: critical

alert: TraefikTLSCertificatesExpiringSoon
annotations:
  description: |
    The minimum number of days until a Traefik-served certificate expires is {{ printf "%.0f" $value }} days on {{ $labels.sans }} which is less than 14 but greater than 7.
  summary: A Traefik-served TLS certificate will expire soon.
expr: |
  max by (instance, sans) ((last_over_time(traefik_tls_certs_not_after{}[5m]) - time()) / 86400) < 14 > 7
for: 5m
labels:
  severity: warning