groups: - name: alert.rules rules: - alert: InstanceDown expr: up{job="node-exporter"} == 0 for: 5m labels: severity: critical annotations: summary: "Endpoint {{ $labels.instance }} down" description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 1 minutes." - alert: InstanceUptime expr: time() - node_boot_time_seconds{job="node-exporter"} >= 7776000 labels: severity: warning annotations: summary: "Uptime of {{ $labels.instance }} more than 90 days" description: "The last reboot of {{ $labels.instance }} was more than 90 days ago"