Spark 分布式SQL引擎，ThriftServer

1.准备：
        分发      

  [/soft/hadoop/etc/hadoop/]
        core-site.xml   
        hdfs-site.xml
  [/soft/hive/conf/]
        hive-site.xml   

        三个文件到所有worker节点的spark/conf目录下

    2.启动spark集群(完全分布式-standalone)      

  $>/soft/spark/sbin/start-all.sh
        master        //201
        worker        //202 ~ 204

    3.创建hive的数据表在默认库下。       

 $>hive -e "create table tt(id int,name string , age int) row format delimited fields terminated by ',' lines terminated by '\n' stored as textfile"

    4.加载数据到hive表中.       

 $>hive -e "load data local inpath 'file:///home/centos/data.txt' into table tt"
 $>hive -e "select * from tt"

    5.启动spark-shell

   $>spark-shell --master spark://s201:7077

    7.启动thriftserver服务器
        $>start-thriftserver.sh  --master spark://s201:7077

 

java 访问：

package com.mao.scala.java;

import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.ResultSet;
import java.sql.Statement;

/**
 * java 通过ThriftServer,spark访问hive
 */
public class ThriftServerClientJava {
    public static void main(String[] args) throws Exception {
        Class.forName("org.apache.hive.jdbc.HiveDriver");
        Connection conn = DriverManager.getConnection("jdbc:hive2://s201:10000");
        Statement st = conn.createStatement();
        ResultSet rs  = st.executeQuery("select count(1) from tt where age > 12 ");
        while(rs.next()){
            int count = rs.getInt(1);
            System.out.println(count);
        }
        rs.close();
    }
}