docker-compose.yml

# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License.  You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied.  See the License for the
# specific language governing permissions and limitations
# under the License.
#

# Basic Airflow cluster configuration for CeleryExecutor with Redis and PostgreSQL.
#
# WARNING: This configuration is for local development. Do not use it in a production deployment.
#
# This configuration supports basic configuration using environment variables or an .env file
# The following variables are supported:
#
# AIRFLOW_IMAGE_NAME           - Docker image name used to run Airflow.
#                                Default: apache/airflow:2.9.3
# AIRFLOW_UID                  - User ID in Airflow containers
#                                Default: 50000
# AIRFLOW_PROJ_DIR             - Base path to which all the files will be volumed.
#                                Default: .
# Those configurations are useful mostly in case of standalone testing/running Airflow in test/try-out mode
#
# _AIRFLOW_WWW_USER_USERNAME   - Username for the administrator account (if requested).
#                                Default: airflow
# _AIRFLOW_WWW_USER_PASSWORD   - Password for the administrator account (if requested).
#                                Default: airflow
# _PIP_ADDITIONAL_REQUIREMENTS - Additional PIP requirements to add when starting all containers.
#                                Use this option ONLY for quick checks. Installing requirements at container
#                                startup is done EVERY TIME the service is started.
#                                A better way is to build a custom image or extend the official image
#                                as described in https://airflow.apache.org/docs/docker-stack/build.html.
#                                Default: ''
#
# Feel free to modify this file to suit your needs.
---
x-airflow-common:
  &airflow-common
  # In order to add custom dependencies or upgrade provider packages you can use your extended image.
  # Comment the image line, place your Dockerfile in the directory where you placed the docker-compose.yaml
  # and uncomment the "build" line below, Then run `docker-compose build` to build the images.
  # image: ${AIRFLOW_IMAGE_NAME:-apache/airflow:2.9.3}
  build:
    context: ./airflow
    dockerfile: Dockerfile
    args:
      AIRFLOW_UID: ${AIRFLOW_UID:-50000}
  environment:
    &airflow-common-env
    AIRFLOW__CORE__EXECUTOR: CeleryExecutor
    AIRFLOW__CELERY__RESULT_BACKEND: db+postgresql://airflow:airflow@postgres_airflow/airflow
    AIRFLOW__CELERY__BROKER_URL: redis://:@redis:6379/0
    AIRFLOW__CORE__FERNET_KEY: ''
    AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION: 'true'
    AIRFLOW__CORE__LOAD_EXAMPLES: 'false'
    AIRFLOW__API__AUTH_BACKENDS: 'airflow.api.auth.backend.basic_auth,airflow.api.auth.backend.session'
    AIRFLOW__DATABASE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres_airflow/airflow  # 여기를 수정
    AWS_ACCESS_KEY_ID: ${AWS_ACCESS_KEY_ID}
    AWS_SECRET_ACCESS_KEY: ${AWS_SECRET_ACCESS_KEY}
    AWS_DEFAULT_REGION: ${AWS_DEFAULT_REGION}
    BUCKET_NAME: ${BUCKET_NAME}
    POSTGRES_HOST: ${DB_HOST}
    POSTGRES_DB: ${DB_NAME}
    POSTGRES_USER: ${DB_USER}
    POSTGRES_PASSWORD: ${DB_PASSWORD}
    POSTGRES_PORT: ${DB_PORT}
    # yamllint disable rule:line-length
    # Use simple http server on scheduler for health checks
    # See https://airflow.apache.org/docs/apache-airflow/stable/administration-and-deployment/logging-monitoring/check-health.html#scheduler-health-check-server
    # yamllint enable rule:line-length
    AIRFLOW__SCHEDULER__ENABLE_HEALTH_CHECK: 'true'
    # WARNING: Use _PIP_ADDITIONAL_REQUIREMENTS option ONLY for a quick checks
    # for other purpose (development, test and especially production usage) build/extend Airflow image.
    # _PIP_ADDITIONAL_REQUIREMENTS: ${_PIP_ADDITIONAL_REQUIREMENTS:-apache-airflow-providers-apache-spark apache-airflow-providers-mysql}
    # The following line can be used to set a custom config file, stored in the local config folder
    # If you want to use it, outcomment it and replace airflow.cfg with the name of your config file
    # AIRFLOW_CONFIG: '/opt/airflow/config/airflow.cfg'
  volumes:
    - ${AIRFLOW_PROJ_DIR:-.}/dags:/opt/airflow/dags
    - ${AIRFLOW_PROJ_DIR:-.}/logs:/opt/airflow/logs
    - ${AIRFLOW_PROJ_DIR:-.}/config:/opt/airflow/config
    - ${AIRFLOW_PROJ_DIR:-.}/plugins:/opt/airflow/plugins
    - big-data-volume:/sources
    - spark-volume:/opt/spark
  # user: "${AIRFLOW_UID:-50000}:0"
  depends_on:
    &airflow-common-depends-on
    redis:
      condition: service_healthy
    postgres_airflow:
      condition: service_healthy
  networks:
    - shared_network

services:
  postgres_airflow:
    image: postgres:13
    container_name: postgres_airflow
    hostname: postgres_airflow 
    environment:
      POSTGRES_USER: airflow
      POSTGRES_PASSWORD: airflow
      POSTGRES_DB: airflow
    volumes:
      - postgres-db-volume:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD", "pg_isready", "-U", "airflow"]
      interval: 10s
      retries: 5
      start_period: 5s
    restart: always
    networks:
      - shared_network

  redis:
    # Redis is limited to 7.2-bookworm due to licencing change
    # https://redis.io/blog/redis-adopts-dual-source-available-licensing/
    image: redis:7.2-bookworm
    expose:
      - 6379
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 30s
      retries: 50
      start_period: 30s
    restart: always
    networks:
      - shared_network

  airflow-webserver:
    <<: *airflow-common
    command: webserver
    ports:
      - "8085:8080"
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:8080/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

  airflow-scheduler:
    <<: *airflow-common
    command: scheduler
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:8974/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

  airflow-worker:
    <<: *airflow-common
    command: celery worker
    healthcheck:
      # yamllint disable rule:line-length
      test:
        - "CMD-SHELL"
        - 'celery --app airflow.providers.celery.executors.celery_executor.app inspect ping -d "celery@$${HOSTNAME}" || celery --app airflow.executors.celery_executor.app inspect ping -d "celery@$${HOSTNAME}"'
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    environment:
      <<: *airflow-common-env
      # Required to handle warm shutdown of the celery workers properly
      # See https://airflow.apache.org/docs/docker-stack/entrypoint.html#signal-propagation
      DUMB_INIT_SETSID: "0"
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

  airflow-triggerer:
    <<: *airflow-common
    command: triggerer
    healthcheck:
      test: ["CMD-SHELL", 'airflow jobs check --job-type TriggererJob --hostname "$${HOSTNAME}"']
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

  airflow-init:
    <<: *airflow-common
    entrypoint: /bin/bash
    # yamllint disable rule:line-length
    command:
      - -c
      - |
        if [[ -z "${AIRFLOW_UID}" ]]; then
          echo
          echo -e "\033[1;33mWARNING!!!: AIRFLOW_UID not set!\e[0m"
          echo "If you are on Linux, you SHOULD follow the instructions below to set "
          echo "AIRFLOW_UID environment variable, otherwise files will be owned by root."
          echo "For other operating systems you can get rid of the warning with manually created .env file:"
          echo "    See: https://airflow.apache.org/docs/apache-airflow/stable/howto/docker-compose/index.html#setting-the-right-airflow-user"
          echo
        fi
        one_meg=1048576
        mem_available=$$(($$(getconf _PHYS_PAGES) * $$(getconf PAGE_SIZE) / one_meg))
        cpus_available=$$(grep -cE 'cpu[0-9]+' /proc/stat)
        disk_available=$$(df / | tail -1 | awk '{print $$4}')
        warning_resources="false"
        if (( mem_available < 4000 )) ; then
          echo
          echo -e "\033[1;33mWARNING!!!: Not enough memory available for Docker.\e[0m"
          echo "At least 4GB of memory required. You have $$(numfmt --to iec $$((mem_available * one_meg)))"
          echo
          warning_resources="true"
        fi
        if (( cpus_available < 2 )); then
          echo
          echo -e "\033[1;33mWARNING!!!: Not enough CPUS available for Docker.\e[0m"
          echo "At least 2 CPUs recommended. You have $${cpus_available}"
          echo
          warning_resources="true"
        fi
        if (( disk_available < one_meg * 10 )); then
          echo
          echo -e "\033[1;33mWARNING!!!: Not enough Disk space available for Docker.\e[0m"
          echo "At least 10 GBs recommended. You have $$(numfmt --to iec $$((disk_available * 1024 )))"
          echo
          warning_resources="true"
        fi
        if [[ $${warning_resources} == "true" ]]; then
          echo
          echo -e "\033[1;33mWARNING!!!: You have not enough resources to run Airflow (see above)!\e[0m"
          echo "Please follow the instructions to increase amount of resources available:"
          echo "   https://airflow.apache.org/docs/apache-airflow/stable/howto/docker-compose/index.html#before-you-begin"
          echo
        fi
        mkdir -p /sources/logs /sources/dags /sources/plugins
        chown -R "${AIRFLOW_UID}:0" /sources/{logs,dags,plugins}
        exec /entrypoint airflow version
    # yamllint enable rule:line-length
    environment:
      <<: *airflow-common-env
      _AIRFLOW_DB_MIGRATE: 'true'
      _AIRFLOW_WWW_USER_CREATE: 'true'
      _AIRFLOW_WWW_USER_USERNAME: ${_AIRFLOW_WWW_USER_USERNAME:-airflow}
      _AIRFLOW_WWW_USER_PASSWORD: ${_AIRFLOW_WWW_USER_PASSWORD:-airflow}
      _PIP_ADDITIONAL_REQUIREMENTS: ''
    user: "0:0"
    volumes:
      - ${AIRFLOW_PROJ_DIR:-.}:/sources


  airflow-cli:
    <<: *airflow-common
    profiles:
      - debug
    environment:
      <<: *airflow-common-env
      CONNECTION_CHECK_MAX_COUNT: "0"
    # Workaround for entrypoint issue. See: https://github.com/apache/airflow/issues/16252
    command:
      - bash
      - -c
      - airflow


  # You can enable flower by adding "--profile flower" option e.g. docker-compose --profile flower up
  # or by explicitly targeted on the command line e.g. docker-compose up flower.
  # See: https://docs.docker.com/compose/profiles/
  flower:
    <<: *airflow-common
    command: celery flower
    profiles:
      - flower
    ports:
      - "5555:5555"
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:5555/"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully
    networks:
      - shared_network

  kafdrop:
    image: obsidiandynamics/kafdrop
    container_name: kafdrop
    ports:
      - "9000:9000"
    environment:
      KAFKA_BROKERCONNECT: broker:29092
    depends_on:
      - broker
    networks:
      - shared_network
      
  zookeeper:
    image: confluentinc/cp-zookeeper:7.0.0
    hostname: zookeeper
    container_name: zookeeper
    environment:
      ZOOKEEPER_SERVER_ID: 1
      ZOOKEEPER_CLIENT_PORT: 2181
      ZOOKEEPER_TICK_TIME: 2000
    volumes: 
      - ./zoo/data:/var/lib/zookeeper/data
      - ./zoo/log:/var/lib/zookeeper/log
    user: root
    networks:
      - shared_network
    
  broker:
    image: confluentinc/cp-kafka:7.0.0
    container_name: broker
    ports:
      - "9092:9092"
      - "29092:29092"
    volumes: 
      - ./broker/data:/var/lib/kafka/data
    depends_on:
      - zookeeper
    environment:
      KAFKA_BROKER_ID: 1
      KAFKA_ZOOKEEPER_CONNECT: 'zookeeper:2181'
      KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: PLAINTEXT:PLAINTEXT,PLAINTEXT_INTERNAL:PLAINTEXT
      KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://localhost:9092,PLAINTEXT_INTERNAL://broker:29092 
      KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1 
      KAFKA_TRANSACTION_STATE_LOG_MIN_ISR: 1 
      KAFKA_TRANSACTION_STATE_LOG_REPLICATION_FACTOR: 1
      KAFKA_LOG_RETENTION_MS: 10000
    user: root
    networks:
      - shared_network

  # connect:
  #   container_name: s3-connect
  #   image: confluentinc/cp-kafka-connect:7.0.0
  #   environment:
  #     CONNECT_BOOTSTRAP_SERVERS: broker:29092
  #     CONNECT_REST_PORT: 8083
  #     CONNECT_GROUP_ID: "connect-cluster"
  #     CONNECT_CONFIG_STORAGE_TOPIC: "connect-configs"
  #     CONNECT_OFFSET_STORAGE_TOPIC: "connect-offsets"
  #     CONNECT_STATUS_STORAGE_TOPIC: "connect-statuses"
  #     CONNECT_KEY_CONVERTER: "org.apache.kafka.connect.storage.StringConverter"
  #     CONNECT_VALUE_CONVERTER: "org.apache.kafka.connect.json.JsonConverter"
  #     CONNECT_INTERNAL_KEY_CONVERTER: org.apache.kafka.connect.json.JsonConverter
  #     CONNECT_INTERNAL_VALUE_CONVERTER: org.apache.kafka.connect.json.JsonConverter
  #     CONNECT_VALUE_CONVERTER_SCHEMAS_ENABLE: "false"
  #     CONNECT_LOG4J_ROOT_LOGLEVEL: "INFO"
  #     CONNECT_PLUGIN_PATH: "/usr/share/java"
  #     CONNECT_REST_ADVERTISED_HOST_NAME: connect
  #     CONNECT_SCHEMAS_ENABLE: "false"
  #     CONNECT_KEY_CONVERTER_SCHEMAS_ENABLE: "false"
  #     CONNECT_ZOOKEEPER_CONNECT: zookeeper:2181
  #   user: root
  #   ports:
  #     - 8083:8083
  #   depends_on:
  #     - broker

  postgres:
    image: postgres:14
    container_name: postgres
    ports:
      - "5432:5432"
    environment:
      POSTGRES_USER: postgres
      POSTGRES_PASSWORD: postgres
      POSTGRES_DB: postgres
    depends_on:
      - broker
    volumes:
      - ./postgres/data:/var/lib/postgresql/data
    networks:
      - shared_network

  # Spark with N workers
  # spark-master:
  #   build:
  #     context: ./spark/master
  #     dockerfile: Dockerfile
  #   container_name: spark-master
  #   hostname: spark-master
  #   ports:
  #     - "4040:4040"
  #     - "8080:8080"
  #     - "7077:7077"
  #     - "8888:8888"
  #   environment:
  #     - SPARK_MODE=master
  #     - SPARK_MASTER_HOST=spark-master
  #     - SPARK_MASTER_PORT=7077
  #     - SPARK_MASTER_WEBUI_PORT=8080
  #     - SPARK_RPC_AUTHENTICATION_ENABLED=no
  #     - SPARK_RPC_ENCRYPTION_ENABLED=no
  #     - SPARK_LOCAL_STORAGE_ENCRYPTION_ENABLED=no
  #     - SPARK_SSL_ENABLED=no
  #     - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID}
  #     - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY}
  #   volumes:
  #     - spark-master-data:/opt/spark/work-dir
  #     - spark-volume:/opt/spark
  #   networks:
  #     - shared_network

  # spark-worker:
  #   build:
  #     context: ./spark/worker
  #     dockerfile: Dockerfile
  #   container_name: spark-worker
  #   hostname: spark-worker
  #   environment:
  #     - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID}
  #     - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY}
  #   depends_on:
  #     - spark-master
  #   ports:
  #     - "8081:8081"
  #   volumes:
  #     - ./sandbox/spark/app:/usr/local/spark/app # Scripts (same path in airflow and spark)
  #     - ./sandbox/spark/resources:/usr/local/spark/resources # Resources (same path in airflow and spark)
  #   networks:
  #     - shared_network

  grafana:
    image: grafana/grafana
    container_name: grafana
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=admin
    volumes:
      - grafana-data:/var/lib/grafana
    networks:
      - shared_network
volumes:
  spark-master-data:
  grafana-data:
  postgres-db-volume:
  big-data-volume:
  spark-volume:

networks:
  shared_network: