分布式搭建(hadoop+hive+spark)

最新推荐文章于 2024-06-13 13:50:52 发布

旖旎沐心

最新推荐文章于 2024-06-13 13:50:52 发布

阅读量645

点赞数

文章标签：分布式 hadoop hive

本文链接：https://blog.csdn.net/m0_48669897/article/details/131531747

版权

地址规划

hadoop-master 192.168.43.141
hadoop-slave1 192.168.43.142
hadoop-slave2 192.168.43.143

核心软件包下载链接

链接：https://pan.baidu.com/s/1OwKLvZAaw8AtVaO_c6mvtw?pwd=1234
提取码：1234
MYSQL5.6：wget http://repo.mysql.com/mysql-community-release-el6-5.noarch.rpm
Scale:wget https://downloads.lightbend.com/scala/2.12.4/scala-2.12.4.tgz

安装前操作（三台主机配置）

iptables -F    #清空系统防火墙
service iptables save    #保存防火墙配置
setenforce 0    #临时关闭内核防火墙

vim /etc/selinux/config    #永久关闭内核防火墙
SELINUX=disabled

修改主机名（三台主机配置）

vim /etc/sysconfig/network
NETWORKING=yes
HOSTNAME=hadoop-master

vim /etc/sysconfig/network
NETWORKING=yes
HOSTNAME=hadoop-slave1

vim /etc/sysconfig/network
NETWORKING=yes
HOSTNAME=hadoop-slave2

修改主机配置文件（三台主机配置）

vim /etc/hosts
192.168.43.141    hadoop-master 
192.168.43.142    hadoop-slave1 
192.168.43.143    hadoop-slave2

SSH配置（三台主机配置）

#生成密钥对（公钥和私钥）
ssh-keygen -t rsa
#三次回车生成密钥
#Execute in Maste
cat /root/.ssh/id_rsa.pub > /root/.ssh/authorized_keys
chmod 600 /root/.ssh/authorized_keys
#追加密钥到Master
ssh 192.168.43.142 cat /root/.ssh/id_rsa.pub >> /root/.ssh/authorized_keys
ssh 192.168.43.143 cat /root/.ssh/id_rsa.pub >> /root/.ssh/authorized_keys
#复制密钥到从节点
scp /root/.ssh/authorized_keys root@192.168.43.142:/root/.ssh/authorized_keys
scp /root/.ssh/authorized_keys root@192.168.43.143:/root/.ssh/authorized_keys

安装jdk（主机配置）

安装JDK
tar zxvf jdk1.8.0_111.tar.gz

#Executer in Maste
#配置JDK环境变量
vim ~/.bashrc
JAVA_HOME=/usr/local/src/jdk1.8.0_111
JAVA_BIN=/usr/local/src/jdk1.8.0_111/bin
JRE_HOME=/usr/local/src/jdk1.8.0_111/jre
CLASSPATH=/usr/local/jdk1.8.0_111/jre/lib:/usr/local/jdk1.8.0_111/lib:/usr/local/jdk1.8.0_111/jre/lib/charsets.jar

PATH=$PATH:$JAVA_HOME/bin:$JRE_HOME/bin
#分发到其他节点
scp /root/.bashrc root@192.168.43.142:/root/.bashrc
scp /root/.bashrc root@192.168.43.143:/root/.bashrc

JDK拷贝到Slave主机
#Executer in Master
scp -r /usr/local/src/jdk1.8.0_111 root@192.168.43.142:/usr/local/src/jdk1.8.0_111
scp -r /usr/local/src/jdk1.8.0_111 root@192.168.43.143:/usr/local/src/jdk1.8.0_111

安装hadoop（主机配置）

tar zxvf hadoop-2.6.1.tar.gz

cd hadoop-2.8.2/etc/hadoop

vim hadoop-env.sh 
export JAVA_HOME=/usr/local/src/jdk1.8.0_111

vim yarn-env.sh
export JAVA_HOME=/usr/local/src/jdk1.8.0_111

vim slaves
hadoop-master
hadoop-slave1
hadoop-slave2

vim core-site.xml
<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://192.168.43.141:9000</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>file:/usr/local/src/hadoop-2.6.1/tmp</value>
</property>
</configuration>

vim hdfs-site.xml
<configuration>
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>hadoop-master:9001</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file:/usr/local/src/hadoop-2.6.1/dfs/name</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file:/usr/local/src/hadoop-2.6.1/dfs/data</value>
</property>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
</configuration>

vim mapred-site.xml
<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
</configuration>

vim yarn-site.xml
<configuration>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>
<value>org.apache.hadoop.mapred.ShuffleHandler</value>
</property>
<property>
<name>yarn.resourcemanager.address</name>
<value>hadoop-master:8032</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address</name>
<value>hadoop-master:8030</value>
</property>
<property>
<name>yarn.resourcemanager.resource-tracker.address</name>
<value>hadoop-master:8035</value>
</property>
<property>
<name>yarn.resourcemanager.admin.address</name>
<value>hadoop-master:8033</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address</name>
<value>hadoop-master:8088</value>
</property>
</configuration>

#创建临时目录和文件目录
mkdir /usr/local/src/hadoop-2.6.1/tmp
mkdir -p /usr/local/src/hadoop-2.6.1/dfs/name
mkdir -p /usr/local/src/hadoop-2.6.1/dfs/data

#配置环境变量
vim ~/.bashrc
HADOOP_HOME=/usr/local/src/hadoop-2.6.1
export PATH=$PATH:$HADOOP_HOME/bin
#刷新环境变量
source ~/.bashrc

#拷贝安装包
scp -r /usr/local/src/hadoop-2.6.1 root@192.168.43.142:/usr/local/src/hadoop-2.6.1
scp -r /usr/local/src/hadoop-2.6.1 root@192.168.43.143:/usr/local/src/hadoop-2.6.1

hadoop namenode -format    #初始化Namenode
./sbin/start-all.sh    #启动集群(特别注意路径)
jps     #状态查看
http://hadoop-master:8088    #查看网页监控

Hive安装

MySQL yum list installed | grep mysql    #查询本地
yum -y remove mysql-libs.x86_64    #将原先的删除
rpm -ivh mysql-community-release-el6-5.noarch.rpm    #进行安解压
yum repolist all | grep mysql    #查看
yum install mysql-community-server -y    #进行安装
chkconfig --list mysqld    #查看是否安装成功
chkconfig mysqld on    #设置开机启动
service mysqld start    #启动mysql服务
mysql -uroot -p （默认密码为空）    #修改密码
use mysql;    #对MySQL库进行操作
update user set authentication_string=password('123456') where user='root';    # 设置账户密码并退出
flush privileges;    #刷新权限
grant all privileges on *.* to 'root'@'%' identified by '123456' with grant option    #MySQL5.6配置远程访问
service mysqld stop    #停止mysql服务
service mysqld start    #启动mysql服务

tar zxvf mysql-connector-java-5.1.45.tar.gz
#复制连接库文件
cp mysql-connector-java-5.1.45/mysql-connector-java-5.1.45-bin.jar /usr/local/src/apache-hive-1.2.2-bin/lib

tar zxvf apache-hive-1.2.2-bin.tar.gz

#修改Hive配置文件
cd apache-hive-1.2.2-bin/conf
vim hive-site.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<property>
 <name>javax.jdo.option.ConnectionURL</name>
<value>jdbc:mysql://hadoop-master:3306/metastore?createDatabaseIfNotExist=true</value>
 <description>JDBC connect string for a JDBC metastore，metastore不存在创建</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>123456</value>
 <description>password to use against metastore database</description>
</property>
</configuration>

#增加环境变量(三台主机配置)
vim ~/.bashrc
export HIVE_HOME=/usr/local/src/apache-hive-1.2.2-bin
export PATH=$HIVE_HOME/bin:$PATH
#刷新环境变量
source ~/.bashrc

#拷贝安装包
scp -r /usr/local/src/apache-hive-1.2.2-bin root@hadoop-slave1:/usr/local/src/apache-hive-1.2.2-bin
scp -r /usr/local/src/apache-hive-1.2.2-bin root@hadoop-slave2:/usr/local/src/apache-hive-1.2.2-bin

#启动HIVE
hive

#解决Terminal initialization failed； falling back to unsupported
cd /usr/local/src/hadoop/share/hadoop/yarn/lib
find jline*    #命令查找jline的jar包
rm-rf jline-2.12.jar    #删除该jar包
#这里可能不是2.12，取决于你自己装的jline的版本,之后将你的hive文件夹下的jline拷贝到hadoop文件夹中去
cp jline-2.12.jar /servers/hadoop/share/hadoop/yarn/lib/

#重启Hadoop集群以及hive。
stop-all.sh
start-all.sh

#启动HIVE
hive

#查看mysql数据库是否有metastore数据表

Spark安装

#解压包
tar zxvf spark-1.6.3-bin-hadoop2.6.tgz
tar zxvf scala-2.12.4.tgz

#修改Spark配置文件
cd /usr/local/src/spark-2.0.2-bin-hadoop2.6/conf
vim spark-env.sh
export SCALA_HOME=/usr/local/src/scala-2.12.4
export JAVA_HOME=/usr/local/src/jdk1.8.0_111
export HADOOP_HOME=/usr/local/src/hadoop-2.6.1
export HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop
SPARK_MASTER_IP=master
SPARK_LOCAL_DIRS=/usr/local/src/spark-2.0.2-bin-hadoop2.6
SPARK_DRIVER_MEMORY=1G

vim slaves
hadoop-slave1
hadoop-slave2

#拷贝安装包
scp -r /usr/local/src/spark-2.0.2-bin-hadoop2.6 root@192.168.43.142:/usr/local/src/spark-2.0.2-bin-hadoop2.6
scp -r /usr/local/src/spark-2.0.2-bin-hadoop2.6 root@192.168.43.143:/usr/local/src/spark-2.0.2-bin-hadoop2.6

scp -r /usr/local/src/scala-2.12.4 root@192.168.43.142:/usr/local/src/scala-2.12.4
scp -r /usr/local/src/scala-2.12.4 root@192.168.43.143:/usr/local/src/scala-2.12.4

#启动集群
cd /usr/local/src/spark-2.0.2-bin-hadoop2.6/sbin
./start-all.sh

#网页监控面板
hadoop-master:8080

#本地模式
./bin/run-example SparkPi 10 --master local[2]

#集群Standlone
./bin/spark-submit --class org.apache.spark.examples.SparkPi --master spark://master:7077 lib/spark-examples-1.6.3-hadoop2.6.0.jar 100

#集群
Spark on Yarn
./bin/spark-submit --class org.apache.spark.examples.SparkPi --master yarn-cluster lib/spark-examples-1.6.3-hadoop2.6.0.jar 10