Commit 3839fc58 authored by Pedro Eduardo Trujillo's avatar Pedro Eduardo Trujillo
Browse files

Merge branch 'dev' into 'master' 

Añade alertas para discos montados de Amazon EBS

See merge request redmic-project/metric/prometheus!11
parents c830ed95 9f0266fb

deploy/docker-compose.dev.yml

+11 −0
Original line number Diff line number Diff line 
version: '3.5'



services:

  prometheus:

    deploy:

      resources:

        limits:

          cpus: '0.5'

          memory: 1G

        reservations:

          cpus: '0.1'

          memory: 256M



volumes:

  prometheus:

    name: ${PROMETHEUS_VOL_NAME:-prometheus-vol}

deploy/docker-compose.prod.yml

+7 −0
Original line number Diff line number Diff line
@@ -6,6 +6,13 @@ services: 
      placement:

        constraints:

          - node.role == worker

      resources:

        limits:

          cpus: '1'

          memory: 2G

        reservations:

          cpus: '0.1'

          memory: 512M



volumes:

  prometheus:

deploy/docker-compose.tmpl.yml

+0 −6
Original line number Diff line number Diff line
@@ -43,12 +43,6 @@ services: 
      restart_policy:

        delay: 10s

        window: 2m

      resources:

        limits:

          cpus: '1'

          memory: 512M

        reservations:

          memory: 128M



networks:

  metric-net:

deploy/rules/swarm_node.rules.prod.yml

+22 −1
Original line number Diff line number Diff line
@@ -42,3 +42,24 @@ groups: 
      description: Swarm node {{ $labels.node_name }} disk is going to fill up in

        6h.

      summary: Disk fill alert for Swarm node '{{ $labels.node_name }}'

  - alert: node_ebs_disk_usage

    expr: ((node_filesystem_size_bytes{mountpoint=~".*/ebs/.*"} - node_filesystem_free_bytes{mountpoint=~".*/ebs/.*"})

      * 100 / node_filesystem_size_bytes{mountpoint=~".*/ebs/.*"}) * ON(instance) GROUP_LEFT(node_name)

      node_meta > 85

    for: 1m

    labels:

      severity: warning

    annotations:

      description: Swarm node {{ $labels.node_name }} EBS disk {{ $labels.mountpoint }} usage is at {{ humanize

        $value}}%.

      summary: EBS disk alert for Swarm node '{{ $labels.node_name }}'

  - alert: node_ebs_disk_fill_rate_6h

    expr: predict_linear(node_filesystem_free_bytes{mountpoint=~".*/ebs/.*"}[1h], 6 * 3600) * ON(instance)

      GROUP_LEFT(node_name) node_meta < 0

    for: 1h

    labels:

      severity: critical

    annotations:

      description: Swarm node {{ $labels.node_name }} EBS disk {{ $labels.mountpoint }} is going to fill up in

        6h.

      summary: EBS disk fill alert for Swarm node '{{ $labels.node_name }}'