stack.yml

version: "3.1"

services:

  monitor:
    image: dockerflow/docker-flow-monitor:${TAG:-latest}
    networks:
      - proxy
      - monitor
    environment:
      - ARG_WEB_EXTERNAL-URL=http://prometheus.dockerflow.com
      - LISTENER_ADDRESS=swarm-listener
      - ARG_ALERTMANAGER_URL=http://alert-manager:9093
    volumes:
      - prom:/data
    deploy:
      labels:
        - com.df.notify=true
        - com.df.distribute=true
        - com.df.serviceDomain=prometheus.dockerflow.com
        - com.df.httpsOnly=true
        - com.df.port=9090
        - com.df.usersPassEncrypted=false
        - com.df.usersSecret=vfarcic
        - com.df.alertName=mem_limit
        - com.df.alertIf=@service_mem_limit:0.8
        - com.df.alertFor=30s
      resources:
        reservations:
          memory: 1750M
        limits:
          memory: 2250M

  alert-manager:
    image: prom/alertmanager
    networks:
      - monitor
    secrets:
      - alert_manager_config
    command: --config.file=/run/secrets/alert_manager_config --storage.path=/alertmanager

  swarm-listener:
    image: dockerflow/docker-flow-swarm-listener
    networks:
      - monitor
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock
    environment:
      - DF_NOTIFY_CREATE_SERVICE_URL=http://monitor:8080/v1/docker-flow-monitor/reconfigure
      - DF_NOTIFY_REMOVE_SERVICE_URL=http://monitor:8080/v1/docker-flow-monitor/remove
    deploy:
      labels:
        - com.df.alertName=mem_limit
        - com.df.alertIf=@service_mem_limit:0.8
        - com.df.alertFor=30s
      placement:
        constraints: [node.role == manager]
      resources:
        reservations:
          memory: 10M
        limits:
          memory: 20M

  docs:
    image: dockerflow/docker-flow-monitor-docs:${TAG:-latest}
    networks:
      - proxy
    deploy:
      labels:
        - com.df.distribute=true
        - com.df.notify=true
        - com.df.reschedule=true
        - com.df.port=80
        - com.df.serviceDomain=monitor.dockerflow.com
        - com.df.servicePath=/
        - com.df.alertName=mem_limit
        - com.df.alertIf=@service_mem_limit:0.8
        - com.df.alertFor=30s
      replicas: 2
      resources:
        reservations:
          memory: 10M
        limits:
          memory: 20M

#   grafana:
#     image: grafana/grafana:${GRAFANA_TAG:-4.6.0}
#     networks:
#       - infra_default
#       - monitor
#     environment:
# #      - GF_SERVER_ROOT_URL=%(protocol)s://%(domain)s:%(http_port)s/grafana/
#       - GF_SECURITY_ADMIN_USER=${GF_USER:-admin}
#       - GF_SECURITY_ADMIN_PASSWORD=${GF_PASS:-admin}
#     deploy:
#       labels:
#         - com.df.notify=true
#         - com.df.distribute=true
#         - com.df.serviceDomain=grafana.dockerflow.com
#         - com.df.port=3000

  cadvisor:
    image: google/cadvisor:${CADVISOR_TAG:-latest}
    networks:
      - monitor
    volumes:
      - /:/rootfs
      - /var/run:/var/run
      - /sys:/sys
      - /var/lib/docker:/var/lib/docker
    deploy:
      mode: global
      labels:
        - com.df.notify=true
        - com.df.scrapePort=8080
        - com.df.alertName=mem_limit
        - com.df.alertIf=@service_mem_limit:0.8
        - com.df.alertFor=30s
      resources:
        reservations:
          memory: 40M
        limits:
          memory: 80M

  node-exporter-manager:
    image: basi/node-exporter:${NODE_EXPORTER_TAG:-v1.14.0}
    networks:
      - monitor
    environment:
      - HOST_HOSTNAME=/etc/host_hostname
      - LOGSPOUT=ignore
    volumes:
      - /proc:/host/proc
      - /sys:/host/sys
      - /:/rootfs
      - /etc/hostname:/etc/host_hostname
    deploy:
      mode: global
      labels:
        - com.df.notify=true
        - com.df.scrapePort=9100
        - com.df.alertName.1=mem_limit_manager
        - com.df.alertIf.1=@node_mem_limit:0.9
        - com.df.alertFor.1=30s
        - com.df.alertName.2=node_mem_limit_total_above
        - com.df.alertIf.2=@node_mem_limit_total_above:0.8
        - com.df.alertFor.2=30s
        - com.df.alertName.3=service_mem_limit
        - com.df.alertIf.3=@service_mem_limit:0.8
        - com.df.alertFor.3=30s
      placement:
        constraints:
          - node.role == manager
      resources:
        reservations:
          memory: 30M
        limits:
          memory: 50M
    command: '-collector.procfs /host/proc -collector.sysfs /host/sys -collector.filesystem.ignored-mount-points "^/(sys|proc|dev|host|etc)($$|/)" -collector.textfile.directory /etc/node-exporter/ -collectors.enabled="conntrack,diskstats,entropy,filefd,filesystem,loadavg,mdadm,meminfo,netdev,netstat,stat,textfile,time,vmstat,ipvs"'

  node-exporter-worker:
    image: basi/node-exporter:${NODE_EXPORTER_TAG:-v1.14.0}
    networks:
      - monitor
    environment:
      - HOST_HOSTNAME=/etc/host_hostname
      - LOGSPOUT=ignore
    volumes:
      - /proc:/host/proc
      - /sys:/host/sys
      - /:/rootfs
      - /etc/hostname:/etc/host_hostname
    deploy:
      mode: global
      labels:
        - com.df.notify=true
        - com.df.scrapePort=9100
        - com.df.alertName.1=mem_limit_worker
        - com.df.alertIf.1=@node_mem_limit:0.9
        - com.df.alertFor.1=30s
        - com.df.alertName.2=node_mem_limit_total_above
        - com.df.alertIf.2=@node_mem_limit_total_above:0.9
        - com.df.alertFor.2=30s
        - com.df.alertName.3=node_mem_limit_total_below
        - com.df.alertIf.3=@node_mem_limit_total_below:0.4
        - com.df.alertFor.3=30s
        - com.df.alertName.4=service_mem_limit
        - com.df.alertIf.4=@service_mem_limit:0.8
        - com.df.alertFor.4=30s
      placement:
        constraints:
          - node.role == worker
      resources:
        reservations:
          memory: 30M
        limits:
          memory: 50M
    command: '-collector.procfs /host/proc -collector.sysfs /host/sys -collector.filesystem.ignored-mount-points "^/(sys|proc|dev|host|etc)($$|/)" -collector.textfile.directory /etc/node-exporter/ -collectors.enabled="conntrack,diskstats,entropy,filefd,filesystem,loadavg,mdadm,meminfo,netdev,netstat,stat,textfile,time,vmstat,ipvs"'

networks:
  monitor:
    external: true
  proxy:
    external: true
  infra_default:
    external: true

secrets:
  alert_manager_config:
    external: true

volumes:
  prom:
    driver: cloudstor:aws
    external: false