1、将Scala安装包上传到syh1虚拟机/etc/packages
2、进入该目录
cd /opt/packages
3、解压到/opt/programs
tar -zxvf scala-2.11.8.tar -C /opt/programs
4、修改文件/etc/profile (3个节点)
vim /etc/profile
末尾添加:
export SCALA_HOME=/opt/programs/scala-2.11.8
export PATH=$PATH:$SCALA_HOME/bin
5、刷新profile (3个节点)
source /etc/profile
6、将scala安装复制到syh1和syh2节点
scp -r /opt/programs/scala-2.11.8 root@syh2:/opt/programs/
scp -r /opt/programs/scala-2.11.8 root@syh3:/opt/programs/
7、将spark包上传到/opt/programs
winSCP
8、切换目录,解压到/opt/programs/
cd /opt/packages
tar -zxvf spark-2.3.3-bin-hadoop2.7.tgz -C /opt/programs
9、进入conf文件夹。将spark-env.template复制一份spark-env.sh
cd /opt/programs/spark-2.3.3-bin-hadoop2.7/conf
cp spark-env.sh.template spark-env.sh
10、修改spark-env.sh,文件末尾添加以下内容
vim spark-env.sh
export JAVA_HOME=/opt/programs/jdk1.8.0_211
export SCALA_HOME=/opt/programs/scala-2.11.8
export HADOOP_HOME=/opt/programs/hadoop-2.7.7
export HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop
export SPARK_MASTER_HOST=syh1
11、将slaves.template文件复制一份为slaves
cp slaves.template slaves
12、修改slaves,改内容
vim slaves
syh2
syh3
13、将syh1节点Spark复制到syh2,syh3节点
scp -r /opt/programs/spark-2.3.3-bin-hadoop2.7 root@syh2:/opt/programs/
scp -r /opt/programs/spark-2.3.3-bin-hadoop2.7 root@syh3:/opt/programs/
14、启动Spark集群
sbin/start-all.sh