Rules

blackbox_tcp

7.952s ago

421.1us

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 7.953s ago 406.8us

extra-checks

3.424s ago

804.3us

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 3.424s ago 445.2us
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 3.424s ago 338us

nginx_alerts

13.683s ago

571.9us

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 13.683s ago 371.3us
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 13.683s ago 178.9us

node_exporter_alerts

6.44s ago

7.474ms

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 6.441s ago 4.212ms
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 6.436s ago 973.6us
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 6.436s ago 1.863ms
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 6.434s ago 371.5us

rabbitmq_alerts

9.14s ago

667us

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 9.14s ago 456.3us
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 9.14s ago 96.61us
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 9.14s ago 92.18us

service_status

5.887s ago

406.7us

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 5.887s ago 390.4us

service_status

12.084s ago

464.4us

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 12.084s ago 444.5us