fix Makefile for production

[homework36]

A strange thing happened: if we run make pull_prod and then make deploy_production then docker will start pulling images with no tag and it cannot start containers properly. Probably something is wrong within the Makefile.
We should have something like

docker pull ddmal/nginx:v3.1.0
docker pull ddmal/rodan-main:v3.1.0
docker pull ddmal/rodan-client:nightly
docker pull ddmal/iipsrv:nightly
docker pull ddmal/rodan-python3-celery:v3.1.0
docker pull ddmal/rodan-gpu-celery:v3.1.0
docker pull redis:alpine
docker pull ddmal/postgres-plpython:v3.1.0
docker pull rabbitmq:alpine

production.yml version used now for record:

services:

  nginx:
    image: "ddmal/nginx:v3.1.0"
    deploy:
      replicas: 1
      resources:
        reservations:
          cpus: "0.5"
          memory: 0.5G
        limits:
          cpus: "0.5"
          memory: 0.5G
      restart_policy:
        condition: any
        delay: 5s
        window: 30s
      placement:
        constraints:
          - node.role == manager
    healthcheck:
      test: ["CMD", "/usr/sbin/service", "nginx", "status"]
      interval: "30s"
      timeout: "10s"
      retries: 10
      start_period: "5m"
    command: /run/start
    environment:
      TZ: America/Toronto
      SERVER_HOST: rodan2.simssa.ca
      TLS: 1
    ports:
      - "80:80"
      - "443:443"
      - "5671:5671"
      - "9002:9002"
    volumes:
      - "resources:/rodan/data"

  rodan-main:
    image: "ddmal/rodan-main:v3.1.0"
    deploy:
      replicas: 1
      resources:
        reservations:
          cpus: "1"
          memory: 5G
        limits:
          cpus: "1"
          memory: 5G
      restart_policy:
        condition: any
        delay: 5s
        window: 30s
      placement:
        constraints:
          - node.role == manager
    healthcheck:
      test: ["CMD-SHELL", "set -x; /usr/bin/curl -H 'User-Agent: docker-healthcheck' http://localhost:8000/api/?format=json || exit 1"]
      interval: "30s"
      timeout: "30s"
      retries: 5
      start_period: "2m"
    command: /run/start
    environment:
      TZ: America/Toronto
      SERVER_HOST: rodan2.simssa.ca
      CELERY_JOB_QUEUE: None
    env_file:
      - ./scripts/production.env
    volumes:
      - "resources:/rodan/data"

  rodan-client:
    image: "ddmal/rodan-client:nightly"
    deploy:
      placement:
        constraints:
          - node.role == manager
    volumes:
        - "./rodan-client/config/configuration.json:/client/configuration.json"

  iipsrv:
    image: "ddmal/iipsrv:nightly"
    volumes:
      - "resources:/rodan/data"

  celery:
    image: "ddmal/rodan-main:v3.1.0"
    deploy:
      replicas: 1
      resources:
        reservations:
          cpus: "0.8"
          memory: 2G
        limits:
          cpus: "0.8"
          memory: 2G
      restart_policy:
        condition: any
        delay: 5s
        window: 30s
      placement:
        constraints:
          - node.role == manager
    healthcheck:
      test: ["CMD", "celery", "inspect", "ping", "-A", "rodan", "--workdir", "/code/Rodan", "-d", "celery@celery", "-t", "30"]
      interval: "30s"
      timeout: "30s"
      start_period: "1m"
      retries: 5
    command: /run/start-celery
    environment:
      TZ: America/Toronto
      SERVER_HOST: rodan2.simssa.ca
      CELERY_JOB_QUEUE: celery
    env_file:
      - ./scripts/production.env
    volumes:
      - "resources:/rodan/data"

  py3-celery:
    image: "ddmal/rodan-python3-celery:v3.1.0"
    deploy:
      replicas: 1
      resources:
        reservations:
          cpus: "1.5"
          memory: 3G
        limits:
          cpus: "1.5"
          memory: 3G
      restart_policy:
        condition: any
        delay: 5s
        window: 30s
      placement:
        constraints:
          - node.role == manager
    healthcheck:
      test: ["CMD", "celery", "inspect", "ping", "-A", "rodan", "--workdir", "/code/Rodan", "-d", "celery@Python3", "-t", "30"]
      interval: "30s"
      timeout: "30s"
      retries: 5
    command: /run/start-celery
    environment:
      TZ: America/Toronto
      SERVER_HOST: rodan2.simssa.ca
      CELERY_JOB_QUEUE: Python3
    env_file:
      - ./scripts/production.env
    volumes:
      - "resources:/rodan/data"

  gpu-celery:
    image: "ddmal/rodan-gpu-celery:v3.1.0"
    deploy:
      replicas: 1
      resources:
        reservations:
          cpus: "1"
          memory: 15G
        limits:
          cpus: "1"
          memory: 15G
      placement:
        constraints:
          - node.role == manager
      restart_policy:
        condition: any
        delay: 5s
        window: 30s
    healthcheck:
      test: ["CMD", "celery", "inspect", "ping", "-A", "rodan", "--workdir", "/code/Rodan", "-d", "celery@GPU", "-t", "30"]
      interval: "30s"
      timeout: "30s"
      retries: 5
    command: /run/start-celery
    environment:
      TZ: America/Toronto
      SERVER_HOST: rodan2.simssa.ca
      CELERY_JOB_QUEUE: GPU
    env_file:
      - ./scripts/production.env
    volumes:
      - "resources:/rodan/data"

  redis:
    image: "redis:alpine"
    deploy:
      replicas: 1
      resources:
        reservations:
          cpus: "0.8"
          memory: 2G
        limits:
          cpus: "0.8"
          memory: 2G
      restart_policy:
        condition: any
        delay: 5s
        window: 30s
      placement:
        constraints:
          - node.role == manager
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 5s
      retries: 5
    environment:
      TZ: America/Toronto

  postgres:
    image: "ddmal/postgres-plpython:v3.1.0"
    deploy:
      replicas: 1
      endpoint_mode: dnsrr
      resources:
        reservations:
          cpus: "1"
          memory: 2G
        limits:
          cpus: "1"
          memory: 2G
      restart_policy:
        condition: any
        delay: 5s
        window: 30s
      placement:
        constraints:
          - node.role == manager
    healthcheck:
      test: ["CMD-SHELL", "pg_isready", "-U", "postgres"]
      interval: 10s
      timeout: 5s
      retries: 5
    environment:
      TZ: America/Toronto
    volumes:
      - "pg_data:/var/lib/postgresql/data"
      - "pg_backup:/backups"
    env_file:
      - ./scripts/production.env

  rabbitmq:
    image: "rabbitmq:alpine"
    deploy:
      replicas: 1
      resources:
        reservations:
          cpus: "0.8"
          memory: 2G
        limits:
          cpus: "0.8"
          memory: 2G
      restart_policy:
        condition: any
        delay: 5s
        window: 30s
      placement:
        constraints:
          - node.role == manager
    healthcheck:
      test: ["CMD", "rabbitmq-diagnostics", "-q", "ping"]
      interval: "30s"
      timeout: "3s"
      retries: 3
    environment:
      TZ: America/Toronto
    env_file:
      - ./scripts/production.env

volumes:
  resources:
  pg_backup:
  pg_data:

[homework36]

Happened again. Need to look into this

[homework36]

I just realize this is probably because of this line in Makefile

Rodan/Makefile

Line 14 in c9c83a9

PROD_TAG := v3.1.0

It should be updated to the newest version (v3.2.0 for now), but it was still the earlier version.
I'll make sure to update this in the next production release, and for now, we will manually edit it on the production server.

[homework36]

The PROD_TAG in Makefile should be updated first.
The documentation (wiki) has been updated as well.