mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-22 17:37:19 +08:00
99 lines
4.2 KiB
YAML
99 lines
4.2 KiB
YAML
groups:
|
|
|
|
- name: RabbitmqExporter
|
|
|
|
|
|
rules:
|
|
|
|
# 1m delay allows a restart without triggering an alert.
|
|
- alert: RabbitmqNodeDown
|
|
expr: 'sum(rabbitmq_build_info) < 3'
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: RabbitMQ node down (instance {{ $labels.instance }})
|
|
description: "Less than 3 nodes running in RabbitMQ cluster\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
# 1m delay allows a restart without triggering an alert.
|
|
- alert: RabbitmqNodeNotDistributed
|
|
expr: 'erlang_vm_dist_node_state < 3'
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: RabbitMQ node not distributed (instance {{ $labels.instance }})
|
|
description: "Distribution link to peer {{ $labels.peer }} is not 'up' (state {{ $value }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: RabbitmqInstancesDifferentVersions
|
|
expr: 'count(count(rabbitmq_build_info) by (rabbitmq_version)) > 1'
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: RabbitMQ instances different versions (instance {{ $labels.instance }})
|
|
description: "Running different version of RabbitMQ in the same cluster, can lead to failure.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: RabbitmqMemoryHigh
|
|
expr: 'rabbitmq_process_resident_memory_bytes / rabbitmq_resident_memory_limit_bytes * 100 > 90 and rabbitmq_resident_memory_limit_bytes > 0'
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: RabbitMQ memory high (instance {{ $labels.instance }})
|
|
description: "A node use more than 90% of allocated RAM\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: RabbitmqFileDescriptorsUsage
|
|
expr: 'rabbitmq_process_open_fds / rabbitmq_process_max_fds * 100 > 90 and rabbitmq_process_max_fds > 0'
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: RabbitMQ file descriptors usage (instance {{ $labels.instance }})
|
|
description: "A node use more than 90% of file descriptors\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: RabbitmqTooManyReadyMessages
|
|
expr: 'sum(rabbitmq_queue_messages_ready) BY (queue) > 1000'
|
|
for: 1m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: RabbitMQ too many ready messages (instance {{ $labels.instance }})
|
|
description: "RabbitMQ too many ready messages on queue {{ $labels.queue }} ({{ $value }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: RabbitmqTooManyUnackMessages
|
|
expr: 'sum(rabbitmq_queue_messages_unacked) BY (queue) > 1000'
|
|
for: 1m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: RabbitMQ too many unack messages (instance {{ $labels.instance }})
|
|
description: "Too many unacknowledged messages on queue {{ $labels.queue }} ({{ $value }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: RabbitmqTooManyConnections
|
|
expr: 'rabbitmq_connections > 1000'
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: RabbitMQ too many connections (instance {{ $labels.instance }})
|
|
description: "The total connections of a node is too high\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: RabbitmqNoQueueConsumer
|
|
expr: 'rabbitmq_queue_consumers < 1'
|
|
for: 1m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: RabbitMQ no queue consumer (instance {{ $labels.instance }})
|
|
description: "A queue has less than 1 consumer\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
# Threshold of 3 avoids noise from occasional misroutes. Adjust based on your expected traffic patterns.
|
|
- alert: RabbitmqUnroutableMessages
|
|
expr: 'increase(rabbitmq_channel_messages_unroutable_returned_total[5m]) > 3 or increase(rabbitmq_channel_messages_unroutable_dropped_total[5m]) > 3'
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: RabbitMQ unroutable messages (instance {{ $labels.instance }})
|
|
description: "A queue has unroutable messages ({{ $value }} in the last 5m)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|