blackbox_tcp |
2.868s ago |
295.8us |
||
| Rule | State | Error | Last Evaluation | Evaluation Time |
| alert: BlackboxTCPFailure expr: probe_success == 0 for: 20s labels: severity: critical annotations: description: 'Blackbox TCP probe to {{ $labels.instance }} (service: {{ $labels.service }}) failed.' summary: TCP connectivity failed for {{ $labels.instance }} | ok | 2.868s ago | 285.1us | |
extra-checks |
13.34s ago |
517.6us |
||
| Rule | State | Error | Last Evaluation | Evaluation Time |
| alert: ServiceDoesNotExist expr: service_exists == 0 for: 1m labels: severity: critical annotations: description: Systemd service '{{ $labels.service }}' is missing on instance {{ $labels.instance }}. summary: Service {{ $labels.service }} does NOT exist | ok | 13.341s ago | 323us | |
| alert: DotnetMissing expr: dotnet_exists == 0 for: 1m labels: severity: critical annotations: description: .NET runtime is NOT installed on instance {{ $labels.instance }}. summary: .NET runtime missing | ok | 13.34s ago | 182.3us | |
nginx_alerts |
8.598s ago |
420.9us |
||
| Rule | State | Error | Last Evaluation | Evaluation Time |
| alert: NginxExporterDown expr: up{job="nginx"} == 0 for: 1m labels: severity: critical annotations: description: Prometheus cannot scrape NGINX metrics. summary: 'NGINX exporter down: {{ $labels.instance }}' | ok | 8.598s ago | 306.5us | |
| alert: NginxHighConnections expr: nginx_connections_active > 1000 for: 2m labels: severity: warning annotations: description: Active connections > 1000 for 2 minutes. summary: High NGINX connections on {{ $labels.instance }} | ok | 8.598s ago | 98.2us | |
node_exporter_alerts |
1.356s ago |
6.249ms |
||
| Rule | State | Error | Last Evaluation | Evaluation Time |
| alert: HighCPUUsage expr: (100 - avg by (instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 90 for: 5m labels: severity: warning annotations: description: CPU usage is above 90% for 5 minutes. summary: High CPU usage on {{ $labels.instance }} | ok | 1.356s ago | 3.39ms | |
| alert: HighMemoryUsage expr: (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100 > 90 for: 5m labels: severity: warning annotations: description: Memory usage is above 90%. summary: High memory usage on {{ $labels.instance }} | ok | 1.353s ago | 819.8us | |
| alert: HighDiskUsage expr: 100 * (1 - node_filesystem_avail_bytes{fstype!~"tmpfs|overlay",job="node_exporter",mountpoint!~"/run.*|/var/lib/docker.*"} / node_filesystem_size_bytes{fstype!~"tmpfs|overlay",job="node_exporter",mountpoint!~"/run.*|/var/lib/docker.*"}) > 90 for: 10m labels: severity: warning annotations: description: Filesystem {{ $labels.device }} mounted at {{ $labels.mountpoint }} is over 90% full. summary: Disk usage high on {{ $labels.instance }} ({{ $labels.mountpoint }}) | ok | 1.352s ago | 1.649ms | |
| alert: NodeDown expr: up{job="node_exporter"} == 0 for: 2m labels: severity: critical annotations: description: Node exporter is not reachable. summary: 'Node down: {{ $labels.instance }}' | ok | 1.351s ago | 372.9us | |
rabbitmq_alerts |
4.057s ago |
780.4us |
||
| Rule | State | Error | Last Evaluation | Evaluation Time |
| alert: RabbitMQExporterDown expr: up{job="rabbitmq"} == 0 for: 2m labels: severity: critical annotations: description: Prometheus cannot scrape RabbitMQ metrics. summary: 'RabbitMQ exporter down: {{ $labels.instance }}' | ok | 4.057s ago | 389.7us | |
| alert: RabbitMQUnackedMessages expr: rabbitmq_queue_messages_unacked > 100 for: 5m labels: severity: warning annotations: description: Queue {{ $labels.queue }} has {{ $value }} unacked messages. summary: Unacked messages high on {{ $labels.instance }} | ok | 4.057s ago | 221.4us | |
| alert: RabbitMQQueueTooLarge expr: rabbitmq_queue_messages_ready > 500 for: 5m labels: severity: warning annotations: description: Queue {{ $labels.queue }} has {{ $value }} ready messages. summary: Queue backlog on {{ $labels.instance }} | ok | 4.057s ago | 151us | |
service_status |
802ms ago |
289.6us |
||
| Rule | State | Error | Last Evaluation | Evaluation Time |
| alert: AnyServiceDown expr: service_running == 0 for: 30s labels: severity: critical annotations: description: Service {{ $labels.service }} is not running on {{ $labels.instance }}. summary: Service {{ $labels.service }} is DOWN on {{ $labels.instance }} | ok | 802ms ago | 277.6us | |
service_status |
6.999s ago |
304.9us |
||
| Rule | State | Error | Last Evaluation | Evaluation Time |
| alert: AnyServiceDown expr: service_running == 0 for: 30s labels: severity: critical annotations: description: Service {{ $labels.service }} has been reported as not running on {{ $labels.instance }}. summary: Service {{ $labels.service }} is DOWN on {{ $labels.instance }} | ok | 6.999s ago | 292.8us | |