mirror of
https://github.com/monitoring-mixins/website.git
synced 2024-12-14 11:37:31 +00:00
44 lines
1.8 KiB
YAML
44 lines
1.8 KiB
YAML
groups:
|
|
- name: ibm-mq-alerts
|
|
rules:
|
|
- alert: IBMMQExpiredMessages
|
|
annotations:
|
|
description: The number of expired messages in the {{$labels.qmgr}} is {{$labels.value}}
|
|
which is above the threshold of 2.
|
|
summary: There are expired messages, which imply that application resilience
|
|
is failing.
|
|
expr: |
|
|
sum without (description,hostname,instance,job,platform) (ibmmq_qmgr_expired_message_count) > 2
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
- alert: IBMMQStaleMessages
|
|
annotations:
|
|
description: A stale message with an age of {{$labels.value}} has been sitting
|
|
in the {{$labels.queue}} which is above the threshold of 300s.
|
|
summary: Stale messages have been detected.
|
|
expr: |
|
|
sum without (description,instance,job,platform) (ibmmq_queue_oldest_message_age) >= 300
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: IBMMQLowDiskSpace
|
|
annotations:
|
|
description: The amount of disk space available for {{$labels.qmgr}} is at {{$labels.value}}%
|
|
which is below the threshold of 5%.
|
|
summary: There is limited disk available for a queue manager.
|
|
expr: |
|
|
sum without (description,hostname,instance,job,platform) (ibmmq_qmgr_queue_manager_file_system_free_space_percentage) <= 5
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
- alert: IBMMQHighQueueManagerCpuUsage
|
|
annotations:
|
|
description: The amount of CPU usage for the queue manager {{$labels.qmgr}}
|
|
is at {{$labels.value}}% which is above the threshold of 85%.
|
|
summary: There is a high CPU usage estimate for a queue manager.
|
|
expr: |
|
|
sum without (description,hostname,instance,job,platform) (ibmmq_qmgr_user_cpu_time_estimate_for_queue_manager_percentage) >= 85
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|