ops/stacks/lvl1/swarmprom/prometheus/rules/swarm_task.rules.yml

25 lines
1.4 KiB
YAML

groups:
- name: /1/store/projects/vagrant/docker-swarm-vagrant/apps/swarmprom/prometheus/rules/swarm_task.rules.yml
rules:
- alert: task_high_cpu_usage_50
expr: sum(rate(container_cpu_usage_seconds_total{container_label_com_docker_swarm_task_name=~".+"}[1m]))
BY (container_label_com_docker_swarm_task_name, container_label_com_docker_swarm_node_id)
* 100 > 50
for: 1m
annotations:
description: '{{ $labels.container_label_com_docker_swarm_task_name }} on ''{{
$labels.container_label_com_docker_swarm_node_id }}'' CPU usage is at {{ humanize
$value}}%.'
summary: CPU alert for Swarm task '{{ $labels.container_label_com_docker_swarm_task_name
}}' on '{{ $labels.container_label_com_docker_swarm_node_id }}'
- alert: task_high_memory_usage_1g
expr: sum(container_memory_rss{container_label_com_docker_swarm_task_name=~".+"})
BY (container_label_com_docker_swarm_task_name, container_label_com_docker_swarm_node_id) > 1e+09
for: 1m
annotations:
description: '{{ $labels.container_label_com_docker_swarm_task_name }} on ''{{
$labels.container_label_com_docker_swarm_node_id }}'' memory usage is {{ humanize
$value}}.'
summary: Memory alert for Swarm task '{{ $labels.container_label_com_docker_swarm_task_name
}}' on '{{ $labels.container_label_com_docker_swarm_node_id }}'