Commit e41879c3 authored by Pedro Eduardo Trujillo's avatar Pedro Eduardo Trujillo
Browse files

Retoca definición de alertas

parent 23ba9e46

deploy/rules/swarm_job.rules.yml

+2 −2
Original line number Diff line number Diff line 
groups:

- name: /1/store/projects/vagrant/docker-swarm-vagrant/apps/swarmprom/prometheus/rules/swarm_job.rules.yml

- name: swarm_job

  rules:

  - alert: backup_db_not_created

    expr: time() - backup_created_date_seconds{} > 86400
@@ -9,7 +9,7 @@ groups: 
      description: Error creating backup for '{{ $labels.label }}' database.

      summary: Error creating backup for '{{ $labels.label }}' database.



  - alert: certificate_renew_not_attemped

  - alert: certificate_renew_not_attempted

    expr: time() - certificates_valid_date_seconds{} > 604800

    labels:

      severity: warning

deploy/rules/swarm_node.rules.yml

+2 −2
Original line number Diff line number Diff line 
groups:

- name: /1/store/projects/vagrant/docker-swarm-vagrant/apps/swarmprom/prometheus/rules/swarm_node.rules.yml

- name: swarm_node

  rules:

  - alert: node_cpu_usage

    expr: 100 - (avg(irate(node_cpu{mode="idle"}[1m]) * ON(instance) GROUP_LEFT(node_name)

      node_meta * 100) BY (node_name)) > 50

      node_meta * 100) BY (node_name)) > 70

    for: 1m

    labels:

      severity: warning

deploy/rules/swarm_service.rules.yml

+7 −7
Original line number Diff line number Diff line 
groups:

- name: /1/store/projects/vagrant/docker-swarm-vagrant/apps/swarmprom/prometheus/rules/swarm_service.rules.yml

- name: swarm_service

  rules:

  - alert: service_in_restart_loop

    expr: avg without(instance)(changes(process_start_time_seconds[1h]) > bool 3) > 0.1

    for: 10m

    labels:

      severity: ticket

      severity: warning

    annotations:

      description: The service '{{ $labels.label }}' has restarted more 3 times in last hour.

      summary: The service '{{ $labels.label }}' has restarted more 3 times in last hour.

      description: Service '{{ $labels.label }}' has been restarted 3 times in last hour.

      summary: Service '{{ $labels.label }}' has been restarted 3 times in last hour.



  - alert: service_down

    expr: up == 0

    for: 5m

    labels:

      severity: severity

      severity: warning

    annotations:

      description: Instance {{ $labels.instance }} down.

      summary: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes."
 
 No newline at end of file
 
      description: Instance '{{ $labels.instance }}' of job {{ $labels.job }} has been down for more than 5 minutes.

      summary: Instance '{{ $labels.instance }}' of job {{ $labels.job }} has been down for more than 5 minutes.
 
 No newline at end of file

deploy/rules/swarm_task.rules.yml

+16 −13
Original line number Diff line number Diff line 
groups:

- name: /1/store/projects/vagrant/docker-swarm-vagrant/apps/swarmprom/prometheus/rules/swarm_task.rules.yml

- name: swarm_task

  rules:

  - alert: task_high_cpu_usage_50

  - alert: task_high_cpu_usage_80

    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

      * 100 > 80

    for: 5m

    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

      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_90

    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) /

      sum(container_spec_memory_limit_bytes{container_label_com_docker_swarm_task_name=~".+"})

      BY (container_label_com_docker_swarm_task_name, container_label_com_docker_swarm_node_id)) > 0.9

    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 }}'
 
        $labels.container_label_com_docker_swarm_node_id }}'' memory usage is at {{ 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 }}'