groups: - name: node_exporters_heartbeat rules: {% for instance in ["vmm", "fw", "infra", "auth", "app"] %} - alert: {{ instance }}_node_exporter_down expr: | (present_over_time(up{instance="{{ instance }}"}[5m]) or on() vector(0)) == 0 for: 30s labels: severity: critical annotations: summary: "Exporter heartbeat is down: {{ instance }}" description: "{{ instance }} exporter is down for 5 mins" {% endfor %} - name: postgresql_heartbeat rules: - alert: Postgresql_Down expr: | (present_over_time(pg_up{instance="infra", job="postgres"}[5m]) or on() vector(0)) == 0 for: 30s labels: severity: critical annotations: summary: "Postgresql Heartbeat Lost: postgresql" description: "postgresql node is down for 5 mins." - name: Certificate_expiry_check rules: {% for filename in ["root.crt", "intermediate.crt", "crowdsec.crt", "blocky.crt", "kopia.crt", "postgresql.crt", "ldap.crt", "prometheus.crt", "loki.crt"] %} - alert: {{ filename | replace('.', '_') }}_is_expired_soon expr: | max(x509_cert_not_after{filename="{{ filename }}"}) - time() < 2592000 for: 1d labels: severity: critical annotations: summary: "{{ filename }} is expired in 30 days" description: "{{ filename }} is expired in 30 days." {% endfor %}