Alerts


/etc/prometheus/alert_rules.yml > nginx_alerts
NginxExporterDown (0 active)
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 }}'
NginxHighConnections (0 active)
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 }}
/etc/prometheus/alert_rules.yml > node_exporter_alerts
HighDiskUsage (1 active)
alert: HighDiskUsage
expr: (node_filesystem_size_bytes
  - node_filesystem_free_bytes) / node_filesystem_size_bytes * 100 > 90
for: 10m
labels:
  severity: warning
annotations:
  description: Filesystem {{ $labels.mountpoint }} is over 90% full.
  summary: Disk usage high on {{ $labels.instance }}
Labels State Active Since Value
alertname="HighDiskUsage" device="/dev/mapper/ubuntu--vg-ubuntu--lv" fstype="ext4" instance="click-r1:9100" job="node_exporter" mountpoint="/" severity="warning" firing 2025-12-07 10:20:59.427195323 +0000 UTC 94.83043690418666
HighCPUUsage (0 active)
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 }}
HighMemoryUsage (0 active)
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 }}
NodeDown (0 active)
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 }}'
/etc/prometheus/alert_rules.yml > rabbitmq_alerts
RabbitMQExporterDown (0 active)
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 }}'
RabbitMQQueueTooLarge (0 active)
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 }}
RabbitMQUnackedMessages (0 active)
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 }}