version: "3.5"

networks:

  net:
    driver: overlay
    driver_opts:
      encrypted: "true"
    attachable: true

volumes:

    alertmanager:
      driver: pxd
      driver_opts:
        repl: 2
        size: 2
    alertmanagerB:
      driver: pxd
      driver_opts:
        repl: 2
        size: 2 
    caddycerts:
      driver: pxd
      driver_opts:
        repl: 2
        size: 1
    grafana:
      driver: pxd
      driver_opts:
        repl: 2
        size: 10
    portainer_data:
      driver: pxd
      driver_opts:
        repl: 2
        size: 10
    portainer_certs:
      driver: pxd
      driver_opts:
        repl: 2
        size: 1
    prometheus:
      driver: pxd
      driver_opts:
        repl: 2
        size: 10
    swarm-endpoints:
      driver: pxd
      driver_opts:
        repl: 2
        size: 1
        shared: "true"

configs:

  alertmanager_config:
    file: ./alertmanager/conf/alertmanager.yml
    name: alertmanager_config$CONFALERTMANANGER

  caddy_config:
    file: ./caddy/Caddyfile
    name: caddy_config$CONFCADDY
  caddy_www:
    file: ./caddy/index.html
    name: caddy_www$CONFCADDY
  #caddy_cert:
  #  file: ./caddy/caddycerts/cert.pem
  #  name: caddy_cert$CONFCADDYCERT
  #caddy_key:
  #  file: ./caddy/caddycerts/key.pem
  #  name: caddy_key$CONFCADDYCERT

  docker_garbage_collection:
    file: ./docker-gc-exclude
    name: docker_garbage_collection$CONFDOCKERGC

  grafana_dashboards_nodes:
    file: ./grafana/dashboards/nodes-netdata-dockerd-cadvisor.json
    #file: ./grafana/dashboards/nodes-node-exporter-dockerd-cadvisor.json
    name: grafana_dashboards_nodes$CONFGRAFANADASH
  grafana_dashboards_containers:
    file: ./grafana/dashboards/containers-netdata-dockerd-cadvisor.json
    #file: ./grafana/dashboards/containers-node-exporter-dockerd-cadvisor.json
    name: grafana_dashboards_containers$CONFGRAFANADASH
  grafana_dashboards_etcd_cluster:
    file: ./grafana/dashboards/etcd-cluster.json
    name: grafana_dashboards_etcd_cluster$CONFGRAFANADASH
  grafana_dashboards_portworx_cluster_status:
    file: ./grafana/dashboards/portworx-cluster-status.json
    name: grafana_dashboards_portworx_cluster_status$CONFGRAFANADASH
  grafana_dashboards_portworx_volumes_status:
    file: ./grafana/dashboards/portworx-volumes-status.json
    name: grafana_dashboards_portworx_volumes_status$CONFGRAFANADASH
  grafana_dashboards_prometheus_2_stats:
    file: ./grafana/dashboards/prometheus-2-stats.json
    name: grafana_dashboards_prometheus_2_stats$CONFGRAFANADASH

  grafana_provisioning_datasources:
    file: ./grafana/datasources/prometheus.yaml
  grafana_provisioning_dashboards:
    file: ./grafana/dashboards.yml

  karma_conf:
    file: ./karma/karma.yaml
    name: karma_conf$CONFKARMA

  prometheus_conf:
    file: ./prometheus/conf/prometheus.yml
    name: prometheus_conf$CONFPROM
  prometheus_rules_nodes:
    file: ./prometheus/rules/nodes.yml
    name: prometheus_rules_nodes$CONFPROMRULES
  prometheus_rules_containers:
    file: ./prometheus/rules/containers.yml
    name: prometheus_rules_containers$CONFPROMRULES
  prometheus_rules_portworx:
    file: ./prometheus/rules/portworx.yml
    name: prometheus_rules_portworx$CONFPROMRULES

services:

  alertmanager:
    image: prom/alertmanager:latest
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
      - '--cluster.listen-address=0.0.0.0:9094'
      - '--cluster.advertise-address=:9094'
      - '--cluster.peer=alertmanagerB:9094'
    configs:
      - source: alertmanager_config
        target: /etc/alertmanager/alertmanager.yml
    deploy:
      labels:
        prometheus.enable: "true"
        prometheus.port: "9093"
        prometheus.path: "/metrics"
      mode: replicated
      placement:
        constraints:
          - node.Labels.storagegroup==RED
      replicas: 1
      resources:
        limits:
          memory: 128M
        reservations:
          memory: 64M
    healthcheck:
      test: "/bin/wget -q -Y off http://localhost:9093/metrics -O /dev/null > /dev/null 2>&1"
      interval: 25s
      timeout: 3s
      start_period: 30s
    networks:
      - net
    volumes:
      - alertmanager:/alertmanager

  alertmanagerB:
    image: prom/alertmanager:latest
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
      - '--cluster.listen-address=0.0.0.0:9094'
      - '--cluster.advertise-address=:9094'
      - '--cluster.peer=alertmanager:9094'
    configs:
      - source: alertmanager_config
        target: /etc/alertmanager/alertmanager.yml
    deploy:
      labels:
        prometheus.enable: "true"
        prometheus.port: "9093"
        prometheus.path: "/metrics"
      mode: replicated
      placement:
        constraints:
          - node.Labels.storagegroup==RED
      replicas: 1
      resources:
        limits:
          memory: 128M
        reservations:
          memory: 64M
    healthcheck:
      test: "/bin/wget -q -Y off http://localhost:9093/metrics -O /dev/null > /dev/null 2>&1"
      interval: 25s
      timeout: 3s
      start_period: 30s
    networks:
      - net
    volumes:
      - alertmanagerB:/alertmanager

  caddy:
    image: swarmstack/caddy:no-stats
    configs:
      - source: caddy_config
        target: /etc/Caddyfile
      - source: caddy_www
        target: /www/index.html
      #- source: caddy_cert
      #  target: /etc/caddycerts/cert.pem
      #- source: caddy_key
      #  target: /etc/caddycerts/key.pem
    deploy:
      labels:
        prometheus.enable: "true"
        prometheus.port: "9180"
        prometheus.path: "/metrics"
      mode: replicated
      placement:
        constraints:
          - node.Labels.storagegroup==RED
      replicas: 1
      resources:
        limits:
          memory: 128M
        reservations:
          memory: 64M
    environment:
      - ADMIN_USER=${ADMIN_USER:-admin}
      - ADMIN_PASSWORD=${ADMIN_PASSWORD:-admin}
      - CADDY_CERT=${CADDY_CERT:-self_signed}
      - CADDY_KEY=${CADDY_KEY:-}
      - CADDY_URL=${CADDY_URL:-}
      - CADDYPATH=/etc/caddycerts
      - PUSH_USER=${PUSH_USER:-pushuser}
      - PUSH_PASSWORD=${PUSH_PASSWORD:-pushpass}
      #- http_proxy=http://proxy.example.com:80
      #- https_proxy=https://proxy.example.com:443
      #- no_proxy=10.0.0.0/8,.example.com
    networks:
      - net
    ports:
      - "80:80"
      - "443:443"
      - "3000:3000"
      - "9000:9000"
      - "9090:9090"
      - "9091:9091"
      - "9093:9093"
      - "9094:9094"
      - "9095:9093"
      - "19998:19999"
    volumes:
      - caddycerts:/etc/caddycerts

  cadvisor:
    image: gcr.io/google-containers/cadvisor:v0.36.0 
    command: -logtostderr -docker_only
    deploy:
      labels:
        prometheus.enable: "true"
        prometheus.port: "8080"
        prometheus.path: "/metrics"
      mode: global
      resources:
        limits:
          memory: 128M
        reservations:
          memory: 64M
    networks:
      - net
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
      - /dev/disk/:/dev/disk:ro
      - /var/run/docker.sock:/var/run/docker.sock:ro

  docker-gc:
    image: clockworksoul/docker-gc-cron:latest
    configs:
      - source: docker_garbage_collection
        target: /etc/docker-gc-exclude
    deploy:
      mode: global
      resources:
        limits:
          memory: 128M
        reservations:
          memory: 64M
    environment:
        - CRON=25 11 * * *
        # By default, docker will not remove an image if it is tagged in multiple repositories. If
        # you have a server running docker where this is the case, for example in CI environments
        # where dockers are being built, re-tagged, and pushed, you can set this flag to 1 to override.
        - FORCE_IMAGE_REMOVAL=1
        # By default, if an error is encountered when cleaning up a container, Docker will report the
        # error back and leave it on disk. This can sometimes lead to containers accumulating. If
        # you run into this issue, you can force the removal of the container by setting this flag.
        - FORCE_CONTAINER_REMOVAL=1
        # By default, docker-gc will not remove a container if it exited less than 1 hour ago.
        # Set the GRACE_PERIOD_SECONDS variable to override this default.
        - GRACE_PERIOD_SECONDS=3600
        # By default, docker-gc will proceed with deletion of containers and images. To test your
        # settings set the DRY_RUN variable to override this default
        - DRY_RUN=0
        # By default, this process will leave any dangling volumes untouched. To instruct the
        # process to automatically clean up any dangling volumes, simply set this value to 1.
        - CLEAN_UP_VOLUMES=0
        # If you don't like all your log output and cron times being in UTC, you can set the
        # TZ variable to override the default.
        #- TZ=America/Chicago
    volumes:
        - /var/run/docker.sock:/var/run/docker.sock

  grafana:
    image: grafana/grafana:latest
    configs:
      - source: grafana_dashboards_containers
        target: /etc/grafana/dashboards/containers.json
      - source: grafana_dashboards_etcd_cluster
        target: /etc/grafana/dashboards/etcd-cluster.json
      - source: grafana_dashboards_nodes
        target: /etc/grafana/dashboards/nodes.json
      - source: grafana_dashboards_portworx_cluster_status
        target: /etc/grafana/dashboards/portworx-cluster-status.json
      - source: grafana_dashboards_portworx_volumes_status
        target: /etc/grafana/dashboards/portworx-volumes-status.json
      - source: grafana_dashboards_prometheus_2_stats
        target: /etc/grafana/dashboards/prometheus-2-stats.json
      - source: grafana_provisioning_dashboards
        target: /etc/grafana/provisioning/dashboards/dashboards.yml
      - source: grafana_provisioning_datasources
        target: /etc/grafana/provisioning/datasources/prometheus.yaml
    deploy:
      labels:
        prometheus.enable: "true"
        prometheus.port: "3000"
        prometheus.path: "/metrics"
      mode: replicated
      placement:
        constraints:
          - node.Labels.storagegroup==RED
      replicas: 1
      resources:
        limits:
          memory: 256M
        reservations:
          memory: 128M
    environment:
      - GF_SECURITY_ADMIN_USER=${ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${ADMIN_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
      #- GF_PATHS_PROVISIONING=/etc/grafana/provisioning/
      #- 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}
      #- http_proxy=http://proxy.example.com:80
      #- https_proxy=https://proxy.example.com:443
      #- no_proxy=10.0.0.0/8,.example.com
    healthcheck:
      test: "wget -q -Y off -O /dev/null http://localhost:3000/login > /dev/null 2>&1"
      interval: 25s
      timeout: 3s
      start_period: 120s
    networks:
      - net
    volumes:
      - grafana:/var/lib/grafana

  karma:
    image: lmierzwa/karma:v0.74
    configs:
      - source: karma_conf
        target: /karma.yaml
    deploy:
      labels:
        prometheus.enable: "true"
        prometheus.port: "8080"
        prometheus.path: "/metrics"
      mode: replicated
      replicas: 1
    networks:
      - net

  kthxbye:
    image: lmierzwa/kthxbye:v0.9
    command:
     - '-alertmanager.uri'
     - 'http://alertmanager:9093'
     - '-extend-if-expiring-in'
     - '5m'
     - '-extend-by'
     - '12h'
     - '-extend-with-prefix'
     - 'ACK'
     - '-interval'
     - '60s'
     - '-max-duration'
     - '0'
    deploy:
      mode: replicated
      replicas: 1
      labels:
        prometheus.enable: "true"
        prometheus.port: "8080"
        prometheus.path: "/metrics"
    networks:
      - net

  portainer:
    image: portainer/portainer:latest
    command: -H tcp://tasks.portainer-agent:9001 --tlsskipverify
    deploy:
      mode: replicated
      placement:
        constraints:
          - node.role == manager
          - node.Labels.storagegroup==RED
      replicas: 1
    networks:
      - net
    volumes:
      - portainer_certs:/certs
      - portainer_data:/data

  portainer-agent:
    image: portainer/agent:latest
    deploy:
      mode: global
      placement:
        constraints: [node.platform.os == linux]
    environment:
      - AGENT_CLUSTER_ADDR=tasks.portainer-agent
      - LOG_LEVEL=warn
    networks:
      - net
    volumes:
      - /var/lib/docker/volumes:/var/lib/docker/volumes
      - /var/run/docker.sock:/var/run/docker.sock

  prometheus:
    image: prom/prometheus:latest
    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.time=48h'
      - '--web.enable-admin-api'
    configs:
      - source: prometheus_conf
        target: /etc/prometheus/prometheus.yml
      - source: prometheus_rules_nodes
        target: /etc/prometheus/nodes.yml
      - source: prometheus_rules_containers
        target: /etc/prometheus/containers.yml
      - source: prometheus_rules_portworx
        target: /etc/prometheus/portworx.yml
    deploy:
      labels:
        prometheus.enable: "true"
        prometheus.port: "9090"
        prometheus.path: "/metrics"
      mode: replicated
      placement:
        constraints:
          - node.Labels.storagegroup==RED
      replicas: 1
      resources:
        limits:
          memory: 2048M
        reservations:
          memory: 1024M
    healthcheck:
      test: "/bin/wget -q -Y off http://localhost:9090/status -O /dev/null > /dev/null 2>&1"
      interval: 25s
      timeout: 3s
      start_period: 60s
    networks:
      - net
    volumes:
      - prometheus:/prometheus
      - swarm-endpoints:/etc/swarm-endpoints/:ro

  pushgateway:
    image: prom/pushgateway:latest
    deploy:
      labels:
        prometheus.enable: "true"
        prometheus.port: "9091"
        prometheus.path: "/metrics"
      mode: replicated
      replicas: 1
      resources:
        limits:
          memory: 512M
        reservations:
          memory: 128M
    healthcheck:
      test: "/bin/wget -q -Y off http://localhost:9091/ -O /dev/null > /dev/null 2>&1"
      interval: 25s
      timeout: 3s
      start_period: 30s
    networks:
      - net

  swarm-discovery-server:
    image: bborysenko/prometheus-swarm-discovery:0.3.0
    command:
      - server
      - -l=warn
    deploy:
      placement:
        constraints:
          - node.role == manager
    networks:
      - net
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock:ro

  swarm-discovery-client:
    image: bborysenko/prometheus-swarm-discovery:0.3.0
    command:
      - client
      - -i=5
      - -s=http://swarm-discovery-server:8080
      - -o=/swarm-endpoints/swarm-endpoints.json
      - -p=swarmstack_prometheus
      - -l=warn
    deploy:
      placement:
        constraints:
          - node.Labels.storagegroup==RED
    networks:
      - net
    volumes:
      - swarm-endpoints:/swarm-endpoints/