hadoop 笔记（hive)

 

//**********************************
//安装配置
1. 修改配置文件

1.1 在conf文件夹下

touch hive-site.xml

<configuration>
<property>
<name>javax.jdo.option.ConnectionURL</name>
<value>jdbc:mysql://localhost:3306/hivedb?createDatabaseIfNotExist=true</value>
<description>JDBC connect string for a JDBC metastore</description>
</property>
<property>
<name>javax.jdo.option.ConnectionDriverName</name>
<value>com.mysql.jdbc.Driver</value>
<description>Driver class name for a JDBC metastore</description>
</property>
<property>
<name>javax.jdo.option.ConnectionUserName</name>
<value>root</value>
<description>username to use against metastore database</description>
</property>
<property>
<name>javax.jdo.option.ConnectionPassword</name>
<value>root</value>
<description>password to use against metastore database</description>
</property>
</configuration>

2. 拷贝mysql驱动包 至 hive/lib下

3. 修改环境变量 ~/.bashrc

export HIVE_HOME=/data/apache-hive-2.3.2-bin
export HADOOP_HOME=/data/hadoop/hadoop-3.0.0
export PATH=$PATH:$HIVE_HOME/bin

注意HADOOP_HOME也是必需要设置的

4. 初始化数据库

schematool -dbType mysql -initSchema

备注：当前采用mysql做为hive的元数据库

1. 出现问题：rg.apache.hadoop.hive.metastore.HiveMetaException: Failed to get schema version.

解决方法进入mysql:GRANT ALL PRIVILEGES ON *.* TO 'root'@'%' IDENTIFIED BY 'root';
flush privileges;

//**********************************
//基本操做

1. 启动客户端
hive --service cli

2. 建立并使用数据库
create database testdb;
use testdb;

备注：出现错误：Unable to instantiate org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient
缘由未出生化数据库

3. 建立一张表

create table users(username string, password string, age int) row format delimited fields terminated by ",";

4. 插入数据

4.1 建立一个数据note.txt

'fred','fred', 30
'sinny', 'sinny', 29

4.2 执行load命令
load data local inpath "/data/data/note.txt" into table users;

遇到问题：
1. There are 0 datanode(s) running and no node(s) are excluded in this operation.
hadoop datanode未启动

解决方案：删除/tmp下hadoop相关文件；删除/usr/local/hadoop/tmp文件 重启

2. 提示hadoop处于安全模式

./hdfs dfsadmin -safemode leave #无用

bin/hadoop fsck / #无用

在hdfs-site.xml中设置安全阀值属性，属性值默认为0.999f，若是设为1则不进行安全检查 # 能够

5. 查询命令

select * from users;