groups: - name: homelab-availability rules: - alert: HomelabExternalConnectivityDown expr: sum(probe_success{job="blackbox-http"} == 0) >= 5 for: 8m labels: severity: warning annotations: summary: "External connectivity appears down" description: "At least 5 public homelab endpoints are unreachable. Likely WAN, DNS, or provider issue." - alert: HomelabEndpointDown expr: (probe_success{job="blackbox-http"} == 0) unless on() (sum(probe_success{job="blackbox-http"} == 0) >= 5) for: 8m labels: severity: critical annotations: summary: "{{ $labels.instance }} is not reachable" description: "Blackbox probe failed for {{ $labels.instance }}." - alert: HomelabEndpointSlow expr: probe_duration_seconds{job="blackbox-http"} > 5 for: 5m labels: severity: warning annotations: summary: "{{ $labels.instance }} is slow" description: "Blackbox probe duration is above 5 seconds for {{ $labels.instance }}." - name: homelab-host rules: - alert: HomelabDiskAlmostFull expr: 100 * (1 - node_filesystem_avail_bytes{fstype!~"tmpfs|overlay"} / node_filesystem_size_bytes{fstype!~"tmpfs|overlay"}) > 85 for: 10m labels: severity: warning annotations: summary: "Disk usage high on {{ $labels.mountpoint }}" description: "{{ $labels.mountpoint }} is above 85% used." - alert: HomelabHighMemoryUsage expr: 100 * (1 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) > 90 for: 10m labels: severity: warning annotations: summary: "Memory usage high" description: "Host memory usage is above 90%." - alert: HomelabTraefik5xx expr: sum(increase(traefik_service_requests_total{code=~"5.."}[5m])) by (service) >= 5 for: 2m labels: severity: warning annotations: summary: "Traefik 5xx responses for {{ $labels.service }}" description: "Traefik reports at least 5 5xx responses for {{ $labels.service }} within 5 minutes."