Alerts

InstanceDown (2 active)
ALERT InstanceDown
  IF up == 0
  FOR 5m
  WITH {service="prometheus_exporter"}
  SUMMARY "Instance {{ $labels.instance }} down"
  DESCRIPTION "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes."
  RUNBOOK ""
Labels State Active Since Value Silence
group="openstack" instance="compute4:9100" job="openstack" service="prometheus_exporter" firing 2021-01-13 09:26:59.705 +0000 UTC 0
group="openstack" instance="compute11:9100" job="openstack" service="prometheus_exporter" firing 2021-01-13 09:26:59.705 +0000 UTC 0
ApiDown (0 active)
ALERT ApiDown
  IF openstack_endpoints_errors > 0
  FOR 15m
  WITH {component="api", service="openstack"}
  SUMMARY "Openstack API {{ $labels.endpoint }} endpoint is down"
  DESCRIPTION "Openstack endpoint {{ $labels.endpoint }} has been down for more than 5 minutes"
  RUNBOOK ""
RabbitQueueGoingCrazy (0 active)
ALERT RabbitQueueGoingCrazy
  IF rabbitmq_queue_messages > 100
  FOR 30m
  SUMMARY "Openstack RabbitMQ queue size is a bit large: {{ $value }}"
  DESCRIPTION "Openstack RabbitMQ queue size is high: {{ $value }} for more than 30 minutes, should check processes"
  RUNBOOK ""
NeutronIpAvailable (0 active)
ALERT NeutronIpAvailable
  IF neutron_net_usage > 400
  FOR 1d
  WITH {component="neutron", service="openstack"}
  SUMMARY "Openstack neutron available IP is low: {{ $value }}"
  DESCRIPTION "Openstack neutron available IP addresses are getting low, used IP: {{ $value }}"
  RUNBOOK ""
VolumePoolUsage (0 active)
ALERT VolumePoolUsage
  IF (cinder_capacity - cinder_free) / cinder_capacity > 0.8
  FOR 5m
  SUMMARY "Cinder pools Size Alert (Over 0.80 Usage)"
  DESCRIPTION "pool show the openstack storage pool (IE : NFS or EqualCloud)"
  RUNBOOK ""
CpuUsage (0 active)
ALERT CpuUsage
  IF avg(1 - irate(node_cpu{mode="idle"}[5m])) BY (instance) > 0.8
  FOR 5m
  SUMMARY "CPU usage"
  DESCRIPTION "CPU Usage rate is beyond 0.8"
  RUNBOOK ""
MemoryUsage (0 active)
ALERT MemoryUsage
  IF 1 - (node_memory_MemAvailable / node_memory_MemTotal) > 0.8
  FOR 5m
  SUMMARY "Mem usage"
  DESCRIPTION "Mem Usage rate is beyond 0.8"
  RUNBOOK ""
DiskUsage (0 active)
ALERT DiskUsage
  IF (node_filesystem_size{mountpoint="/"} - node_filesystem_free) / node_filesystem_size > 0.85
  FOR 5m
  SUMMARY "Disk usage"
  DESCRIPTION "Disk usage rate is beyond 0.85"
  RUNBOOK ""
NeutronIpInactive (0 active)
ALERT NeutronIpInactive
  IF neutron_net_usage{status="DOWN"} > 10
  FOR 1d
  WITH {component="neutron", service="openstack"}
  SUMMARY "Openstack neutron IP is inactive status: {{ $value }}"
  DESCRIPTION "Openstack neutron IP addresses in inactive status is getting high, inactive IP: {{ $value }}"
  RUNBOOK ""