Hive环境搭建

hive 环境搭建需要hadoop的环境。hadoop环境的搭建不在这里赘述。参考：http://www.cnblogs.com/parkin/p/6952370.html

1.准备阶段

hive 官网下载 ： http://mirror.bit.edu.cn/apache/hive/hive-2.1.1/

2.解压缩

tar -zxvf apache-hive-2.1.1-bin.tar.gz -C /home/q/

3.hive 配置

　　hive-env.sh 配置

cp hive-env.sh.template hive-env.sh
vi hive-env.sh
#添加以下代码
export HADOOP_HOME=/home/q/hadoop-2.6.5
export HIVE_HOME=/home/q/apache-hive-2.1.1-bin

　　hive-site.xml 配置

cp hive-site.xml.template hive-site.xml 
vi hive-site.xml
#添加以下代码
  <!-- metastore 数据库位置，这里采用remote形式，数据库名为hive，用户root, 密码 b6f3g2 ，需先创建好。-->
  <property>
    <name>javax.jdo.option.ConnectionURL</name>
    <value>jdbc:mysql://192.168.251.114:3306/hive?createDatabaseIfNotExist=true&characterEncoding=UTF-8</value>
  </property>

  <property>
    <name>javax.jdo.option.ConnectionDriverName</name>
    <value>com.mysql.jdbc.Driver</value>
  </property>

  <property>
    <name>javax.jdo.option.DetachAllOnCommit</name>
    <value>true</value>
    <description>detaches all objects from session so that they can be used after transaction is committed</description>
  </property>

  <property>
    <name>javax.jdo.option.NonTransactionalRead</name>
    <value>true</value>
    <description>reads outside of transactions</description>
  </property>

  <property>
    <name>javax.jdo.option.ConnectionUserName</name>
    <value>root</value>
  </property>

  <property>
    <name>javax.jdo.option.ConnectionPassword</name>
    <value>b6f3g2</value>
  </property>

  <property>
    <name>javax.jdo.option.Multithreaded</name>
    <value>true</value>
    <description>Set this to true if multiple threads access metastore through JDO concurrently.</description>
  </property>

  <property>
    <name>hive.metastore.warehouse.dir</name>
    <value>/user/hive/warehouse</value>
    <description>location of default database for the warehouse</description>
  </property>

  <property>
    <name>hive.exec.scratchdir</name>
    <value>/user/hive/scratch</value>
  </property>

  <property>
    <name>hive.aux.jars.path</name>
    <value>file:///home/q/apache-hive-2.1.1-bin/auxlib/json-serde-1.3.1-SNAPSHOT-jar-with-dependencies.jar,file:///home/q/apache-hive-2.1.1-bin/auxlib
/qunar-udf.jar,file:///home/q/apache-hive-2.1.1-bin/auxlib/brickhouse-0.7.1-SNAPSHOT.jar,file:///home/q/apache-hive-2.1.1-bin/auxlib/joda-time-2.1.jar
</value>
  </property>

  <property>
    <name>hbase.zookeeper.quorum</name>     <value>localhost</value>
  </property>

  <property>
    <name>hive.exec.dynamic.partition</name>
    <value>true</value>
  </property>

  <property>
    <name>hive.exec.dynamic.partition.mode</name>
    <value>nostrict</value>
  </property>

  <property>
    <name>hive.server2.thrift.port</name>
    <value>12121</value>
  </property>

  <property>
    <name>mapred.max.split.size</name>
    <value>48000000</value>
  </property>

  <property>
    <name>mapred.min.split.size.per.node</name>
    <value>24000000</value>
  </property>

  <property>
    <name>mapred.min.split.size.per.rack</name>
    <value>24000000</value>
  </property>

  <property>
    <name>hive.hadoop.supports.splittable.combineinputformat</name>
    <value>true</value>
  </property>

  <property>
    <name>hive.exec.max.dynamic.partitions.pernode</name>
    <value>1000</value>
  </property>

  <property>
    <name>hive.merge.mapredfiles</name>
    <value>true</value>
  </property>

  <property>
    <name>hive.merge.smallfiles.avgsize</name>
    <value>32000000</value>
  </property>
  <property>
    <name>hive.hadoop.supports.splittable.combineinputformat</name>
    <value>true</value>
  </property>

  <property>
   <name>hive.metastore.schema.verification</name>
   <value>false</value>
    <description>
    Enforce metastore schema version consistency.
    True: Verify that version information stored in metastore matches with one from Hive jars.  Also disable automatic
          schema migration attempt. Users are required to manully migrate schema after Hive upgrade which ensures
          proper metastore schema migration. (Default)
    False: Warn if the version information stored in metastore doesn't match with one from in Hive jars.
    </description>
 </property>   

 <property>
   <name>hive.server2.long.polling.timeout</name>
   <value>5000</value>
   <description>Time in milliseconds that HiveServer2 will wait, before responding to asynchronous calls that use long polling</description>
 </property>

</configuration>

　

4.metastore 数据库初始化

cd /home/q/apache-hive-2.1.-bin/bin
schematool -dbType mysql -initSchema

5. hive 启动

# CLI 交互式查询 hive 仓库
cd /home/q/apache-hive-2.1.-bin/bin
./hive

6.hive metastore 服务启动 （主要用于hive client客户端的访问）

cd /home/q/apache-hive-2.1.-bin/bin
hive --service metastore # -p <port_num> 不指定该参数，则默认端口为9083#

7.hiveserver2 服务启动（主要用于rpc方式访问hive数据仓库的表）

cd /home/q/apache-hive-2.1.-bin/bin
./hiveserver2