--- groups: - name: BlackBoxAllInstances rules: - alert: SiteUp expr: probe_success{job="blackbox http-down"} == 1 annotations: title: '{{ $labels.instance }} is UP!' description: '{{ $labels.instance }} is now up!' labels: value: "{{ $value }}" severity: 'critical' - alert: SiteDown expr: probe_success{job="blackbox http-up"} == 0 for: 5m annotations: title: '{{ $labels.instance }} is Down' description: >- {{ $labels.instance }} has been down for more than 5 minutes. labels: value: "{{ $value }}" severity: 'warning' - alert: CertExpLess30days expr: (probe_ssl_earliest_cert_expiry{job="blackbox internal tls"}-time()) < 2592000 annotations: title: '{{ $labels.cname }} will expire soon' description: >- The certificate {{ $labels.cname }} on {{ $labels.instance }} will expire in {{ $value | humanizeDuration }}, it's time to renew it. labels: value: "{{ $value }}" severity: 'warning' - alert: CertExpLess10days expr: (probe_ssl_earliest_cert_expiry{job="blackbox internal tls"}-time()) < 864000 annotations: title: '{{ $labels.cname }} expiracy is imminent!' description: >- The certificate {{ $labels.cname }} on {{ $labels.instance }} will expire in {{ $value | humanizeDuration }}! labels: value: "{{ $value }}" severity: 'critical' ...