使用docker搭建hive测试环境

Posted 2023-02-18 麒思妙想

前连天有读者提问，想让我搞一下calcite查询hive，然而无奈发现calcite本身有个bug，暂时无法通过 calcite jdbc 链接 hive。 暂时没时间提pr fix这个问题，所以先把hive环境搭建记录下来把

环境搭建

docker-compose.yml

version: "3"

services:
  namenode:
    image: bde2020/hadoop-namenode:2.0.0-hadoop2.7.4-java8
    volumes:
      - namenode:/hadoop/dfs/name
    environment:
      - CLUSTER_NAME=test
    env_file:
      - ./hadoop-hive.env
    ports:
      - "20070:50070"
  datanode:
    image: bde2020/hadoop-datanode:2.0.0-hadoop2.7.4-java8
    volumes:
      - datanode:/hadoop/dfs/data
    env_file:
      - ./hadoop-hive.env
    environment:
      SERVICE_PRECONDITION: "namenode:50070"
    ports:
      - "20075:50075"
  hive-server:
    image: bde2020/hive:2.3.2-postgresql-metastore
    env_file:
      - ./hadoop-hive.env
    environment:
      HIVE_CORE_CONF_javax_jdo_option_ConnectionURL: "jdbc:postgresql://hive-metastore/metastore"
      SERVICE_PRECONDITION: "hive-metastore:9083"
    ports:
      - "10000:10000"
  hive-metastore:
    image: bde2020/hive:2.3.2-postgresql-metastore
    env_file:
      - ./hadoop-hive.env
    command: /opt/hive/bin/hive --service metastore
    environment:
      SERVICE_PRECONDITION: "namenode:50070 datanode:50075 hive-metastore-postgresql:5432"
    ports:
      - "9083:9083"
  hive-metastore-postgresql:
    image: bde2020/hive-metastore-postgresql:2.3.0
  presto-coordinator:
    image: shawnzhu/prestodb:0.181
    ports:
      - "7080:8080"

volumes:
  namenode:
  datanode:

networks:
  common-network:
    driver: overlay

hadoop-hive.env

HIVE_SITE_CONF_javax_jdo_option_ConnectionURL=jdbc:postgresql://hive-metastore-postgresql/metastore
HIVE_SITE_CONF_javax_jdo_option_ConnectionDriverName=org.postgresql.Driver
HIVE_SITE_CONF_javax_jdo_option_ConnectionUserName=hive
HIVE_SITE_CONF_javax_jdo_option_ConnectionPassword=hive
HIVE_SITE_CONF_datanucleus_autoCreateSchema=false
HIVE_SITE_CONF_hive_metastore_uris=thrift://hive-metastore:9083
HDFS_CONF_dfs_namenode_datanode_registration_ip___hostname___check=false

HIVE_SITE_CONF_hive_server2_thrift_bind_host=0.0.0.0
HIVE_SITE_CONF_hive_server2_thrift_port=10000
HIVE_SITE_CONF_hive_metastore_event_db_notification_api_auth=false


CORE_CONF_fs_defaultFS=hdfs://namenode:8020
CORE_CONF_hadoop_http_staticuser_user=root
CORE_CONF_hadoop_proxyuser_hive_hosts=*
CORE_CONF_hadoop_proxyuser_hive_groups=*
CORE_CONF_hadoop_proxyuser_hue_hosts=*
CORE_CONF_hadoop_proxyuser_hue_groups=*
CORE_CONF_hadoop_proxyuser_root_hosts=*
CORE_CONF_hadoop_proxyuser_root_groups=*

HDFS_CONF_dfs_webhdfs_enabled=true
HDFS_CONF_dfs_permissions_enabled=false

YARN_CONF_yarn_log___aggregation___enable=true
YARN_CONF_yarn_resourcemanager_recovery_enabled=true
YARN_CONF_yarn_resourcemanager_store_class=org.apache.hadoop.yarn.server.resourcemanager.recovery.FileSystemRMStateStore
YARN_CONF_yarn_resourcemanager_fs_state___store_uri=/rmstate
YARN_CONF_yarn_nodemanager_remote___app___log___dir=/app-logs
YARN_CONF_yarn_log_server_url=http://historyserver:8188/applicationhistory/logs/
YARN_CONF_yarn_timeline___service_enabled=true
YARN_CONF_yarn_timeline___service_generic___application___history_enabled=true
YARN_CONF_yarn_resourcemanager_system___metrics___publisher_enabled=true
YARN_CONF_yarn_resourcemanager_hostname=resourcemanager
YARN_CONF_yarn_timeline___service_hostname=historyserver
YARN_CONF_yarn_resourcemanager_address=resourcemanager:8032
YARN_CONF_yarn_resourcemanager_scheduler_address=resourcemanager:8030
YARN_CONF_yarn_resourcemanager_resource__tracker_address=resourcemanager:8031

测试

启动docker环境

docker-compose up -d

测试代码

package com.dafei1288;

import java.sql.*;

public class Test 
    public static void main(String[] args) 
        String driverName = "org.apache.hive.jdbc.HiveDriver";

        try 
            Class.forName(driverName);
         catch (ClassNotFoundException e) 
            e.printStackTrace();
            System.exit(1);
        

        try
            Connection con = DriverManager.getConnection("jdbc:hive2://172.30.214.156:10000", "", "");
            Statement stmt = con.createStatement();

            String sql = "select count(1)";
            sql = "select * from pokes";
            System.out.println("Running: " + sql);
            ResultSet res = stmt.executeQuery(sql);
            while (res.next()) 
                System.out.println(String.valueOf(res.getString(1)));
            
         catch (SQLException e) 
            e.printStackTrace();
        
    

测试结果