本文的主線 系統 => 集羣 => 測試
本文基於Spark搭建 之 單機模式以及Spark第一個應用
系統
保證集羣ssh互通
hostname
sudo hostname master
# sudo hostname slave01
# sudo hostname slave02
sudo vim /etc/hostname
# master or slave01 or slave02
hosts
sudo vim /etc/hosts
# 192.168.1.29 master
# 192.168.1.30 slave01
# 192.168.1.31 slave02
集羣
# master
cd /opt/services
wget https://mirror.tuna.tsinghua.edu.cn/apache/spark/spark-2.4.7/spark-2.4.7-bin-hadoop2.7.tgz
tar xf spark-2.4.7-bin-hadoop2.7.tgz
mv spark-2.4.7-bin-hadoop2.7 spark
cd spark
cp conf/slaves.template conf/slaves
vim conf/slaves
# slave01
# slave02
cp conf/spark-env.sh.template conf/spark-env.sh
vim conf/spark-env.sh
# export JAVA_HOME=/opt/services/jdk
# SPARK_MASTER_PORT=master
# SPARK_MASTER_PORT=7077
scp -r /opt/services/spark [email protected]:/opt/services
scp -r /opt/services/spark [email protected]:/opt/services
方法1
# master
/opt/services/spark/sbin/start-all.sh
方法2
# master
/opt/services/spark/sbin/start-master.sh
# slave01 & slave02
/opt/services/spark/sbin/start-slave.sh spark://master:7077
測試
# slave01
echo apple >> /opt/services/spark/README.md
# slave02
echo blue >> /opt/services/spark/README.md
/opt/services/spark/bin/spark-submit --class "SimpleApp" --master spark://master:7077 ~/HelloSpark.jar
# Lines with a: 61, Lines with b: 31