Commit 026a5d99 authored by Pedro Eduardo Trujillo's avatar Pedro Eduardo Trujillo
Browse files

Pisa config de despliegue original, aumentándola 

Incorpora uso de Traefik como proxy, omite Caddy original.
Limita más los recursos asignados.
Actualiza definición de CI.
parent 60d355e8

.env

0 → 100644
+2 −0
Original line number Diff line number Diff line 
PUBLIC_HOSTNAME=localhost

UI_AUTH=user:hashpass

.gitlab-ci.yml

+24 −9
Original line number Diff line number Diff line
@@ -8,16 +8,21 @@ deploy-dev: 
    GIT_SUBMODULE_STRATEGY: normal

    DOCKER_DRIVER: overlay2

    SSH_REMOTE: ${DEV_SSH_REMOTE}

    DEPLOY_DIR_NAME: swarmprom

    DEPLOY_DIR_NAME: '.'

    STATUS_CHECK_DELAY: 60

    STACK: metric

    SERVICES_TO_CHECK: metric_dockerd-exporter metric_cadvisor metric_grafana metric_alertmanager metric_unsee metric_node-exporter metric_prometheus metric_caddy

    SERVICES_TO_CHECK: metric_dockerd-exporter metric_cadvisor metric_grafana metric_alertmanager metric_unsee metric_node-exporter metric_prometheus

    ADMIN_USER: ${DEV_ADMIN_USER}

    ADMIN_PASSWORD: ${DEV_ADMIN_PASSWORD}

    UI_AUTH: ${DEV_UI_AUTH}

    PUBLIC_HOSTNAME: ${DEV_PUBLIC_HOSTNAME}

  services:

    - docker:dind

  script:

    - deploy.sh ADMIN_USER=${ADMIN_USER} ADMIN_PASSWORD=${ADMIN_PASSWORD}

    - create-nets.sh metric-net

    - >

      deploy.sh ADMIN_USER=${ADMIN_USER} ADMIN_PASSWORD=${ADMIN_PASSWORD} UI_AUTH=${UI_AUTH}

      PUBLIC_HOSTNAME=${PUBLIC_HOSTNAME}

  environment:

    name: dev

  only:
@@ -31,16 +36,21 @@ deploy-supporting-branch: 
    GIT_SUBMODULE_STRATEGY: normal

    DOCKER_DRIVER: overlay2

    SSH_REMOTE: ${DEV_SSH_REMOTE}

    DEPLOY_DIR_NAME: swarmprom

    DEPLOY_DIR_NAME: '.'

    STATUS_CHECK_DELAY: 60

    STACK: metric

    SERVICES_TO_CHECK: metric_dockerd-exporter metric_cadvisor metric_grafana metric_alertmanager metric_unsee metric_node-exporter metric_prometheus metric_caddy

    SERVICES_TO_CHECK: metric_dockerd-exporter metric_cadvisor metric_grafana metric_alertmanager metric_unsee metric_node-exporter metric_prometheus

    ADMIN_USER: ${DEV_ADMIN_USER}

    ADMIN_PASSWORD: ${DEV_ADMIN_PASSWORD}

    UI_AUTH: ${DEV_UI_AUTH}

    PUBLIC_HOSTNAME: ${DEV_PUBLIC_HOSTNAME}

  services:

    - docker:dind

  script:

    - deploy.sh ADMIN_USER=${ADMIN_USER} ADMIN_PASSWORD=${ADMIN_PASSWORD}

    - create-nets.sh metric-net

    - >

      deploy.sh ADMIN_USER=${ADMIN_USER} ADMIN_PASSWORD=${ADMIN_PASSWORD} UI_AUTH=${UI_AUTH}

      PUBLIC_HOSTNAME=${PUBLIC_HOSTNAME}

  environment:

    name: dev

  only:
@@ -57,16 +67,21 @@ deploy-pro: 
    GIT_SUBMODULE_STRATEGY: normal

    DOCKER_DRIVER: overlay2

    SSH_REMOTE: ${PRO_SSH_REMOTE}

    DEPLOY_DIR_NAME: swarmprom

    DEPLOY_DIR_NAME: '.'

    STATUS_CHECK_DELAY: 60

    STACK: metric

    SERVICES_TO_CHECK: metric_dockerd-exporter metric_cadvisor metric_grafana metric_alertmanager metric_unsee metric_node-exporter metric_prometheus metric_caddy

    SERVICES_TO_CHECK: metric_dockerd-exporter metric_cadvisor metric_grafana metric_alertmanager metric_unsee metric_node-exporter metric_prometheus

    ADMIN_USER: ${PRO_ADMIN_USER}

    ADMIN_PASSWORD: ${PRO_ADMIN_PASSWORD}

    UI_AUTH: ${PRO_UI_AUTH}

    PUBLIC_HOSTNAME: ${PRO_PUBLIC_HOSTNAME}

  services:

    - docker:dind

  script:

    - deploy.sh ADMIN_USER=${ADMIN_USER} ADMIN_PASSWORD=${ADMIN_PASSWORD}

    - create-nets.sh metric-net

    - >

      deploy.sh ADMIN_USER=${ADMIN_USER} ADMIN_PASSWORD=${ADMIN_PASSWORD} UI_AUTH=${UI_AUTH}

      PUBLIC_HOSTNAME=${PUBLIC_HOSTNAME}

  environment:

    name: pro

  only:

docker-compose.yml

0 → 100644
+240 −0
Original line number Diff line number Diff line 
version: '3.5'



services:

  dockerd-exporter:

    image: stefanprodan/caddy

    environment:

      - DOCKER_GWBRIDGE_IP=172.18.0.1

    networks:

      - metric-net

    configs:

      - source: dockerd_config

        target: /etc/caddy/Caddyfile

    deploy:

      mode: global

      restart_policy:

        condition: on-failure

        delay: 1m

        window: 3m

      resources:

        limits:

          cpus: '0.5'

          memory: 128M

        reservations:

          memory: 64M



  cadvisor:

    image: google/cadvisor

    command: -logtostderr -docker_only

    networks:

      - metric-net

    volumes:

      - /var/run/docker.sock:/var/run/docker.sock:ro

      - /:/rootfs:ro

      - /var/run:/var/run

      - /sys:/sys:ro

      - /var/lib/docker/:/var/lib/docker:ro

    deploy:

      mode: global

      restart_policy:

        condition: on-failure

        delay: 1m

        window: 3m

      resources:

        limits:

          cpus: '0.5'

          memory: 128M

        reservations:

          memory: 64M



  grafana:

    image: stefanprodan/swarmprom-grafana:5.0.1

    environment:

      - GF_SECURITY_ADMIN_USER=${ADMIN_USER:-admin}

      - GF_SECURITY_ADMIN_PASSWORD=${ADMIN_PASSWORD:-admin}

      - GF_USERS_ALLOW_SIGN_UP=false

      #- GF_SERVER_ROOT_URL=${GF_SERVER_ROOT_URL:-localhost}

      #- GF_SMTP_ENABLED=${GF_SMTP_ENABLED:-false}

      #- GF_SMTP_FROM_ADDRESS=${GF_SMTP_FROM_ADDRESS:-grafana@test.com}

      #- GF_SMTP_FROM_NAME=${GF_SMTP_FROM_NAME:-Grafana}

      #- GF_SMTP_HOST=${GF_SMTP_HOST:-smtp:25}

      #- GF_SMTP_USER=${GF_SMTP_USER}

      #- GF_SMTP_PASSWORD=${GF_SMTP_PASSWORD}

    networks:

      - metric-net

      - traefik-net

    volumes:

      - grafana:/var/lib/grafana

    deploy:

      mode: replicated

      replicas: 1

      labels:

        traefik.port: "3000"

        traefik.docker.network: traefik-net

        traefik.frontend.rule: Host:grafana.${PUBLIC_HOSTNAME}

        traefik.backend: grafana

      placement:

        constraints:

          - node.role == manager

      restart_policy:

        condition: on-failure

        delay: 1m

        window: 3m

      resources:

        limits:

          cpus: '0.5'

          memory: 128M

        reservations:

          memory: 64M



  alertmanager:

    image: stefanprodan/swarmprom-alertmanager:v0.14.0

    command:

      - '--config.file=/etc/alertmanager/alertmanager.yml'

      - '--storage.path=/alertmanager'

    environment:

      - SLACK_URL=${SLACK_URL:-https://hooks.slack.com/services/TOKEN}

      - SLACK_CHANNEL=${SLACK_CHANNEL:-general}

      - SLACK_USER=${SLACK_USER:-alertmanager}

    networks:

      - metric-net

      - traefik-net

    volumes:

      - alertmanager:/alertmanager

    deploy:

      mode: replicated

      replicas: 1

      labels:

        traefik.port: "9093"

        traefik.docker.network: traefik-net

        traefik.frontend.auth.basic: ${UI_AUTH}

        traefik.frontend.rule: Host:alertmanager.${PUBLIC_HOSTNAME}

        traefik.backend: alertmanager

      placement:

        constraints:

          - node.role == manager

      restart_policy:

        condition: on-failure

        delay: 1m

        window: 3m

      resources:

        limits:

          cpus: '0.5'

          memory: 128M

        reservations:

          memory: 64M



  unsee:

    image: cloudflare/unsee:v0.8.0

    networks:

      - metric-net

      - traefik-net

    environment:

      - "ALERTMANAGER_URIS=default:http://alertmanager:9093"

    deploy:

      mode: replicated

      replicas: 1

      labels:

        traefik.port: "8080"

        traefik.docker.network: traefik-net

        traefik.frontend.auth.basic: ${UI_AUTH}

        traefik.frontend.rule: Host:unsee.${PUBLIC_HOSTNAME}

        traefik.backend: unsee

      restart_policy:

        condition: on-failure

        delay: 1m

        window: 3m

      resources:

        limits:

          cpus: '0.5'

          memory: 128M

        reservations:

          memory: 64M



  node-exporter:

    image: stefanprodan/swarmprom-node-exporter:v0.15.2

    command:

      - '--path.sysfs=/host/sys'

      - '--path.procfs=/host/proc'

      - '--collector.textfile.directory=/etc/node-exporter/'

      - '--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|host|etc)($$|/)'

      # no collectors are explicitely enabled here, because the defaults are just fine,

      # see https://github.com/prometheus/node_exporter

      # disable ipvs collector because it barfs the node-exporter logs full with errors on my centos 7 vm's

      - '--no-collector.ipvs'

    environment:

      - NODE_ID={{.Node.ID}}

    networks:

      - metric-net

    volumes:

      - /proc:/host/proc:ro

      - /sys:/host/sys:ro

      - /:/rootfs:ro

      - /etc/hostname:/etc/nodename

    deploy:

      mode: global

      restart_policy:

        condition: on-failure

        delay: 1m

        window: 3m

      resources:

        limits:

          cpus: '0.5'

          memory: 128M

        reservations:

          memory: 64M



  prometheus:

    image: stefanprodan/swarmprom-prometheus:v2.2.0-rc.0

    command:

      - '--config.file=/etc/prometheus/prometheus.yml'

      - '--web.console.libraries=/etc/prometheus/console_libraries'

      - '--web.console.templates=/etc/prometheus/consoles'

      - '--storage.tsdb.path=/prometheus'

      - '--storage.tsdb.retention=24h'

    networks:

      - metric-net

      - traefik-net

    volumes:

      - prometheus:/prometheus

    configs:

      - source: node_rules

        target: /etc/prometheus/swarm_node.rules.yml

      - source: task_rules

        target: /etc/prometheus/swarm_task.rules.yml

    deploy:

      mode: replicated

      replicas: 1

      labels:

        traefik.port: "9090"

        traefik.docker.network: traefik-net

        traefik.frontend.auth.basic: ${UI_AUTH}

        traefik.frontend.rule: Host:prometheus.${PUBLIC_HOSTNAME}

        traefik.backend: prometheus

      placement:

        constraints:

          - node.role == manager

      restart_policy:

        condition: on-failure

        delay: 1m

        window: 3m

      resources:

        limits:

          cpus: '0.5'

          memory: 512M

        reservations:

          memory: 128M



networks:

  metric-net:

    external: true

  traefik-net:

    external: true



configs:

  dockerd_config:

    file: ./swarmprom/dockerd-exporter/Caddyfile

  node_rules:

    file: ./swarmprom/prometheus/rules/swarm_node.rules.yml

  task_rules:

    file: ./swarmprom/prometheus/rules/swarm_task.rules.yml