部署
安装依赖
基础依赖
JDK 1.8 +
Maven 3.3.6
Git
Python
要求Python版本 2.6 or 2.7
cd /home/hadoop/software
wget https://www.python.org/ftp/python/2.7.6/Python-2.7.6.tgz
tar -zxvf /home/hadoop/software/Python-2.7.6.tgz -C /home/hadoop/app
cd /home/hadoop/app/Python-2.7.6/
./configure --prefix=/home/hadoop/app/Python-2.7.6/
make
make install
# 加入环境变量
vi ~/.bash_profile
export PYTHON_HOME=/home/hadoop/app/Python-2.7.6
export PATH=$PYTHON_HOME/bin:$PATH
pip
安装pip
mkdir ~/app/pip
cd ~/app/pip
curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py
python get-pip.py
pip安装相关Python包
pip install ipython
pip install ipdb
pip install werkzeug
pip install windmill
pip install logilab-astng
其它依赖
sudo yum install ant asciidoc cyrus-sasl-devel cyrus-sasl-gssapi cyrus-sasl-plain gcc gcc-c++ krb5-devel libffi-devel libxml2-devel libxslt-devel make mysql mysql-devel openldap-devel python-devel sqlite-devel gmp-devel
HUE准备
下载HUE:
http://archive.cloudera.com/cdh5/cdh/5/hue-3.9.0-cdh5.7.0.tar.gz
http://archive.cloudera.com/cdh5/cdh/5/hue-3.9.0-cdh5.7.0-src.tar.gz
上传至源码统一存放地址: /home/hadoop/source
解压
tar -xzvf /home/hadoop/source/hue-3.9.0-cdh5.7.0.tar.gz -C /home/hadoop/app
编译命令
cd /home/hadoop/app/hue-cdh5.7.0-release
make apps
集成
Hadoop
# HDFS
vi /home/hadoop/app/hadoop-2.6.0-cdh5.7.0/etc/hadoop/hdfs-site.xml
<property>
<name>dfs.namenode.http-address</name>
<value>hadoop000:50070</value>
</property>
<property>
<name>dfs.webhdfs.enabled</name>
<value>true</value>
</property>
# YARN
vi /home/hadoop/app/hadoop-2.6.0-cdh5.7.0/etc/hadoop/core-site.xml
<property>
<name>hadoop.proxyuser.hue.hosts</name>
<value>*</value>
</property>
<property>
<name>hadoop.proxyuser.hue.groups</name>
<value>*</value>
</property>
Hive
# 拷贝Hive的配置文件
cp /home/hadoop/app/hive-1.1.0-cdh5.7.0/conf/hive-site.xml /home/hadoop/app/hue-3.9.0-cdh5.7.0/desktop/conf
修改配置文件
vi /home/hadoop/app/hue-3.9.0-cdh5.7.0/desktop/conf/hue.ini
secret_key=8732A93E3166430080A4952F669C0332
http_host=hadoop000
http_port=8000
time_zone=Asia/Shanghai
default_hdfs_superuser=hadoop
[hadoop]
[[hdfs_clusters]]
[[[default]]]
fs_defaultfs=hdfs://hadoop000:9000
webhdfs_url=http://hadoop000:50070/webhdfs/v1
hadoop_conf_dir='/home/hadoop/app/hadoop-2.6.0-cdh5.7.0/etc/hadoop'
[[yarn_clusters]]
[[[default]]]
resourcemanager_host=hadoop000
resourcemanager_port=8032
submit_to=True
resourcemanager_api_url=http://hadoop000:8088
proxy_api_url=http://hadoop000:8088
history_server_api_url=http://hadoop000:19888
# 使用MySQL作为HUE运行库
[[database]]
engine=mysql
host=hadoop000
port=3306
user=root
password=12abAB
name=hue_desktop
## options={}
#RDBMS 支持
[[[mysql]]]
nice_name="MySql-MetaStore"
name=hive_basic
engine=mysql
host=hadoop000
port=3306
user=root
password=12abAB
#Spark支持
[spark]
# Host address of the Livy Server.
livy_server_host=hadoop000
# Port of the Livy Server.
livy_server_port=8998
# Configure livy to start in local 'process' mode, or 'yarn' workers.
livy_server_session_kind=yarn
# If livy should use proxy users when submitting a job.
livy_impersonation_enabled=true
# Host of the Sql Server
sql_server_host=hadoop000
# Port of the Sql Server
sql_server_port=10000
初始化 MySQL 库
#需要提前在MySQL创建库:hue_desktop (前面配的HUE MySQL运行库名)
/home/hadoop/app/hue-3.9.0-cdh5.7.0/build/env/bin/hue syncdb
/home/hadoop/app/hue-3.9.0-cdh5.7.0/build/env/bin/hue migrate
启动
# HUE 启动需要前置启动 1.hadoop 2.hiveserver2
#启动HUE
/home/hadoop/app/hue-3.9.0-cdh5.7.0/build/env/bin/supervisor