4.Hive安装

1.系统版本信息

OS：Debian-8.2
Jdk:1.8.0_181
Hadoop:2.8.4
Zookeeper:3.9.10
Hbase:1.4.6
Hive:2.3.3

主机信息

192.168.74.131  master
192.168.74.133  slave1
192.168.74.134  slave2
192.168.74.135  slave3

2.只需在master上安装hive

A:下载Hive-2.3.3

wget https://mirrors.tuna.tsinghua.edu.cn/apache/hive/hive-2.3.3/apache-hive-2.3.3-bin.tar.gz, 镜像地址：https://mirrors.tuna.tsinghua.edu.cn/apache/hive/

B:解压，移动到指定文件夹

tar zxvf apache-hive-2.3.3-bin.tar.gz
mv apache-hive-2.3.3-bin /home/hadoop/opt/
cd /home/hadoop/opt/
mv apache-hive-2.3.3-bin hive-2.3.3

C:添加环境变量

sudo vim /etc/profile
#Set Hive Path
export HIVE_HOME=/home/hadoop/opt/hive-2.3.3
export PATH=$PATH:$HIVE_HOME/bin

#立即生效
source /etc/profile

D:修改配置文件

cd /home/hadoop/opt/hive-2.3.3/conf
cp hive-default.xml.template hive-site.xml
cp hive-env.sh.template hive-env.sh

#hive-env.sh

HADOOP_HOME=/home/hadoop/opt/hadoop-2.8.4
export HIVE_CONF_DIR=/home/hadoop/opt/hive-2.3.3/conf

#hive-site.xml

<!-- HDFS路径hive表的存放位置-->
<property>
 <name>hive.metastore.warehouse.dir</name>
 <value>hdfs://master:9000/hive/warehouse</value>
  </property>
<!--HDFS路径，用于存储不同 map/reduce 阶段的执行计划和这些阶段的中间输出结果。 -->
  <property>
    <name>hive.exec.scratchdir</name>
    <value>hdfs://master:9000/tmp/hive</value>
  </property>

  <property>
    <name>hive.exec.local.scratchdir</name>
    <value>/home/hadoop/opt/hive-2.3.3/tmp</value>
  </property>

  <property>
    <name>hive.downloaded.resources.dir</name>
    <value>/home/hadoop/opt/hive-2.3.3/tmp/${hive.session.id}_resources</value>
  </property>

根据配置文件 ，在hadoop文件系统中创建相应的目录，一定记得修改文件权限

#hdfs 需要启动
hdfs dfs -mkdir -p /tmp/hive
hdfs dfs -mkdir -p /hive/warehouse 

hdfs dfs -chmod 733 /tmp/hive
hdfs dfs -chmod 733 /hive/warehouse

然后在hive的安装根目录下

mkdir tmp

E:启动Hive测试，需要注意的是需要在hive安装目录下的bin目录下执行hive命令，否则会报错

/home/hadoop/opt/hive-2.3.3/bin/hive
show tables; 
create table smq (name string ,count int,status string) row format delimited  fields terminated by '\t' stored as textfile ;
LOAD DATA LOCAL INPATH ' /usr/local/hive1.2/test.txt' OVERWRITE INTO TABLE smq;
select * from smq; 
exit;

 测试2 

# 搭建hadoop时的world count例子中将README.txt上传到hdfs上/test/input/README.txt

CREATE EXTERNAL TABLE `test`(
  `source` string COMMENT '')
STORED AS INPUTFORMAT 
  'org.apache.hadoop.mapred.TextInputFormat' 
OUTPUTFORMAT 
  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
LOCATION
  'hdfs://master:9000/test/input/'
;

show create table test;

select * from test;

3.可能出现的问题和解决方案

问题A:Exception in thread "main" java.lang.RuntimeException: Hive metastore database is not initialized. Please use schematool (e.g. ./schematool -initSchema -dbType ...) to create the schema. If needed, don't forget to include the option to auto-create the underlying database in your JDBC connection string (e.g. ?createDatabaseIfNotExist=true for mysql)

问题B:Error: FUNCTION 'NUCLEUS_ASCII' already exists. (state=X0Y68,code=30000)

解决方法如下：

cd /home/hadoop/opt/hive-2.3.3/bin
#1. 将metastore_db更名为：metastore_db.tmp
mv metastore_db metastore_db.tmp

#2. schematool -initSchema -dbType derby
schematool -initSchema -dbType derby

#启动hive进行检测
/home/hadoop/opt/hive-2.3.3/bin/hive