RabbitMQ监控方法以及焦点指标 - ToB企服应用市场:ToB评测及商务社交产业平台

# 启用插件
rabbitmq-plugins enable prometheus_rabbitmq_exporter
# 查看插件
rabbitmq-plugins list

复制代码

curl -s localhost:15692/metrics

复制代码

# 启用插件
rabbitmq-plugins enable rabbitmq_prometheus
# 查看插件
rabbitmq-plugins list

复制代码

curl -s localhost:15692/metrics

复制代码

# 需要创建用户名和密码:
rabbitmqctl add_user user pass
# 需要将用户赋予管理员权限:
rabbitmqctl set_user_tags user administrator
# 需要将用户赋予vhost权限:
rabbitmqctl set_permissions -p / user ".*" ".*" ".*"

复制代码

cd /usr/local/rabbitmq_exporter-0.29.0.linux-amd64
RABBIT_USER=guest RABBIT_PASSWORD=guest OUTPUT_FORMAT=json PUBLIC_PORT=15692 RABBIT_URL=http://localhost:15672 ./rabbitmq_exporter

复制代码

# 通过promethues协议暴露指标
curl http://localhost:15692/metrics

复制代码

- job_name: rabbitmq
static_configs:
- targets: ['172.19.0.2:15692','172.19.0.3:15692','172.19.0.4:15692']
labels:
instance: rabbitmq

复制代码

groups:
- name: RabbitMQ节点宕机
rules:
- alert: RabbitmqNodeDown
expr: sum(rabbitmq_build_info) < 3
for: 0m
labels:
severity: error
annotations:
summary: "Rabbitmq node down (instance {{ $labels.instance }})"
description: "RabbitMQ集群中运行的节点少于3个\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- name: RabbitMQ节点未分发
rules:
- alert: RabbitmqNodeNotDistributed
expr: erlang_vm_dist_node_state < 3
for: 0m
labels:
severity: warning
annotations:
summary: "Rabbitmq node not distributed (instance {{ $labels.instance }})"
description: "RabbitMQ集群分发链接状态未启动\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- name: RabbitMQ内存高于90%
rules:
- alert: RabbitmqMemoryHigh
expr: rabbitmq_process_resident_memory_bytes / rabbitmq_resident_memory_limit_bytes * 100 > 90
for: 2m
labels:
severity: warning
annotations:
summary: "Rabbitmq memory high (instance {{ $labels.instance }})"
description: "RabbitMQ集群节点使用超过90%的已分配 RAM\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- name: RabbitMQ未确认消息过高
rules:
- 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: "RabbitMQ集群未确认的消息大于1000\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- name: RabbitMQ节点总连接数太高
rules:
- alert: RabbitmqTooManyConnections
expr: rabbitmq_connections > 1000
for: 2m
labels:
severity: warning
annotations:
summary: "Rabbitmq too many connections (instance {{ $labels.instance }})"
description: "RabbitMQ集群节点的总连接数大于1000\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- name: RabbitMQ没有队列消费者
rules:
- alert: RabbitmqNoQueueConsumer
expr: rabbitmq_queue_consumers < 1
for: 1m
labels:
severity: warning
annotations:
summary: "Rabbitmq no queue consumer (instance {{ $labels.instance }})"
description: "RabbitMQ集群队列的消费者少于1个\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"

复制代码

rabbitmqctl cluster_status

复制代码