hive-compose.yml

version: '3.9'
# https://github.com/apache/hive/blob/master/packaging/src/docker/docker-compose.yml 
services:
  postgres:
    # The postgres:16 image uses Debian as its base, and has some issues
    image: postgres:16-alpine
    restart: unless-stopped
    container_name: postgres
    hostname: postgres
    environment:
      POSTGRES_DB: 'metastore_db'
      POSTGRES_USER: 'hive'
      POSTGRES_PASSWORD: 'password'
    ports:
      - '5432:5432'
    volumes:
      - hive-db:/var/lib/postgresql
  # access cmd is `psql metastore_db hive`, don't forget the database arg, otherwrise, `FATAL:  database "hive" does not exist`
  metastore:
    image: apache/hive:${HIVE_VERSION}
    depends_on:
      - postgres
    restart: unless-stopped
    container_name: metastore
    hostname: metastore
    environment:
      DB_DRIVER: postgres
      SERVICE_NAME: 'metastore'
      SERVICE_OPTS: '-Xmx1G -Djavax.jdo.option.ConnectionDriverName=org.postgresql.Driver
                     -Djavax.jdo.option.ConnectionURL=jdbc:postgresql://postgres:5432/metastore_db
                     -Djavax.jdo.option.ConnectionUserName=hive
                     -Djavax.jdo.option.ConnectionPassword=password'
      # HIVE_CUSTOM_CONF_DIR: /hive_custom_conf # can't replace hive-site.xml
    ports:
        - '9083:9083'
    volumes:
        - type: bind
          source: hive/postgresql-42.5.1.jar
          target: /opt/hive/lib/postgres.jar
        - type: bind
          source: hive/conf/hive-site.xml
          target: /opt/hive/conf/hive-site.xml
        # maybe needless(we always access hive by hs2)
        - type: bind
          source: hive/conf/core-site.xml
          target: /opt/hadoop/etc/hadoop/core-site.xml
  # hiveserver2 should have all configs 
  hiveserver2:
    image: apache/hive:${HIVE_VERSION}
    depends_on:
      - metastore
    restart: unless-stopped
    container_name: hiveserver2
    environment:
      HIVE_SERVER2_THRIFT_PORT: 10000
      SERVICE_OPTS: '-Xmx1G -Dhive.metastore.uris=thrift://metastore:9083'
      IS_RESUME: 'true'
      SERVICE_NAME: 'hiveserver2'
    ports:
      - '10000:10000'
      - '10002:10002'
    volumes:
      - type: bind
        source: hive/postgresql-42.5.1.jar
        target: /opt/hive/lib/postgres.jar
      - type: bind
        source: hive/conf/hive-site.xml
        target: /opt/hive/conf/hive-site.xml
      # for create db(hdfs dir) permission issue `/tmp/hive on HDFS should be writable. Current permissions are: rwxr-xr-x`
      - type: bind
        source: hive/conf/core-site.xml
        target: /opt/hadoop/etc/hadoop/core-site.xml
volumes:
  hive-db:
# hive_db

# The volume persists the metadata of Hive tables inside Postgres container.

# warehouse

# The volume stores tables' files inside HiveServer2 container.
# docker exec -it hiveserver2 beeline -u 'jdbc:hive2://hiveserver2:10000/'
networks:
  default:
    name: ${NETWORK_NAME}
    external: true