大数据集群搭建 *** 作

大数据集群搭建 *** 作 1.安装ntp

rpm -qa|grep ntp
yum install ntp -y

2.删除mariadb

rpm -aq | grep mariadb
rpm -e --nodeps mariadb-libs- 版本

3.安装mysql

rpm -ivh mysql-community-common
...		libs
...		libs-compat
...		client
...		server

4.修改主机名

hostnamectl set-hostname xxx
bash

5.关闭防火墙

systemctl status firewalld
systemctl stop firewalld
systemctl disable firewalld

6.hosts映射

vi /etc/hosts

7.修改时区

tzselect
TZ="Asia/Shanghai";export TZ

8.屏蔽默认server，设master为本地时钟源，服务器层级设为10

vi /etc/ntp.conf
server 127.127.0.1
fudge 127.127.0.1 stratum 10

让硬件时间与系统时间同步
vi  /etc/sysconfig/ntpd
OPTIONS="-g"
SYNC_HWCLOCK=yes

9.主节点开启ntp，从节点同步

service ntpd start
crontab -e
*/30 10-17 * * * /usr/sbin/ntpdate master

10.免密

ssh-keygen -t rsa  回车三次
ssh-copy-id master

11.环境变量

vi /etc/profile

export JAVA_HOME=/usr/software/java/jdk1.8.0_91
export PATH=$PATH:$JAVA_HOME/bin
export ZOOKEEPER_HOME=/usr/software/zookeeper/zookeeper-3.4.14
export PATH=$PATH:$ZOOKEEPER_HOME/bin
export HADOOP_HOME=/usr/software/hadoop/hadoop-2.7.7
export PATH=$PATH:$HADOOP_HOME/bin
export PATH=$PATH:$HADOOP_HOME/sbin
export HIVE_HOME=/usr/software/hive/apache-hive-2.3.4-bin
export PATH=$PATH:$HIVE_HOME/bin

source /etc/profile

12.zookeeper

mv zoo_sample.cfg zoo.cfg

dataDir=/usr/zookeeper/zookeeper-3.4.14/zkdata/
dataLogDir=/usr/zookeeper/zookeeper-3.4.14/zkdatalog/
server.1=master:2888:3888
server.2=slave1:2888:3888
server.3=slave2:2888:3888

mkdir zkdata
mkdir zkdatalog

cd zkdata
touch myid

bin/zkServer.sh start

13.hadoop

mv $HADOOP_HOME/etc/hadoop
hadoop-env.sh
export HADOOP_HOME=/usr/software/hadoop/hadoop-2.7.7

core-site.xml

	
		fs.default.name
		hdfs://master:9000
	
	
		hadoop.tmp.dir
		/usr/hadoop/hadoop-2.7.3/hdfs/tmp
	

hdfs-site.xml

	
		dfs.namenode.name.dir
		/usr/software/hadoop/hadoop-2.7.7/hdfs/name
	
	
		dfs.datanode.data.dir
		/usr/software/hadoop/hadoop-2.7.7/hdfs/data
	
	
		dfs.replication
		2
	

yarn-env.sh

export HADOOP_HOME=/usr/software/hadoop/hadoop-2.7.7

yarn-site.xml

	
		yarn.resourcemanager.admin.address
		master:18141
	
	
		yarn.nodemanager.aux-services
		mapreduce_shuffle
	

cp mapred-site.xml.template mapred-site.xml

	
		mapreduce.framework.name
		yarn
	

/etc/hadoop/新建master/slaves文件

touch master
master
touch slaves
slave1
slave2

格式化：在master执行

hadoop namenode -format

14.数据仓库 是否安装mysql并开启服务

rpm -aq | grep mysql-community-server
systemctl status mysqld
生成临时密码
grep "temporary password" /var/log/mysqld.log

登录

mysql -uroot -p

set global validate_password_policy=0;
set global validate_password_length=6;
alter user'root'@'localhost'identified by '123456';
grant all privileges on *.* to 'root'@'%' identified by '123456' with grant option;
flush privileges;

hive-env.sh

mv hive-env.sh.template hive-env.sh
export HADOOP_HOME=/usr/software/hadoop/hadoop-2.7.7

hive-site.xml

--------------------------------master-------------------------------------



	
	    hive.metastore.warehouse.dir
	    /user/hive_remote/warehouse
	  
	
	
	    hive.metastore.local
	    false
	
	
	
	    hive.metastore.uris
	    thrift://slave1:9083
	


--------------------------------slave1----------------------------------


  
    
        hive.metastore.warehouse.dir
        /user/hive_remote/warehouse
    
    
    
        javax.jdo.option.ConnectionURL
        jdbc:mysql://slave2:3306/hive?createDatabaseIfNotExist=true&characterEncoding=UTF-8&useSSL=false
	   JDBC connect string for a JDBC metastore
    
    
    
        javax.jdo.option.ConnectionDriverName
        com.mysql.jdbc.Driver
    
    
    
        javax.jdo.option.ConnectionUserName
        root
    
    
    
        javax.jdo.option.ConnectionPassword
        123456
    
    
        hive.metastore.schema.verification
        false
    
    
        datanucleus.schema.autoCreateALL
        true
    

mysql lib包
cp mysql-connector-java-5.1.47-bin.jar /usr/hive/apache-hive-2.1.1-bin/lib

jline冲突
cp jline-2.12.jar /usr/hadoop/hadoop-2.7.3/share/hadoop/yarn/lib

slave1上执行，初始化数据库
schematool -dbType mysql -initSchema

slave1上执行
cd /usr/hive/apache-hive-2.1.1-bin
bin/hive --service metastore

master上执行
cd /usr/hive/apache-hive-2.1.1-bin
bin/hive