Spark

• 安装

  cd /usr/app
  wget https://archive.apache.org/dist/spark/spark-2.0.0/spark-2.0.0-bin-hadoop2.7.tgz
  tar -zxvf spark-2.0.0-bin-hadoop2.7.tgz spark-2.0.0-bin-hadoop2.7
  

• 添加环境变量

  vi /etc/profile
  # 添加以下内容
  export Spark_HOME=/usr/app/spark-2.0.0-bin-hadoop2.7
  export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HBASE_HOME/bin:$HIVE_HOME/bin:$Fl
  ume_HOME/bin:$Spark_HOME/bin:$Scala_HOME/bin
  

• 配置./conf/slaves

  /usr/app/spark-2.0.0-bin-hadoop2.7/conf/
  
  # 首先将 slaves.template 拷贝一份
  cp -r slaves.template slaves
  # 修改 slaves 文件,添加
  hadoop11
  hadoop12
  hadoop13
  

• 配置./conf/spark-env.sh

  #将 spark-env.sh. template 拷贝一份
  cp -r spark-env.sh.template spark-env.sh
  vi /conf/spark-env.sh
  #添加以下内容
  export JAVA_HOME=/usr/app/jdk1.8.0_77
  export Scala_HOME=scala-2.11.11
  export SPARK_MASTER_IP=hadoop11
  export SPARK_WORKER_MEMORY=2g
  export MASTER=spark://hadoop11:7077
  

• 将 spark-2.0.0-bin-hadoop2.7 文件夹拷贝到另外两个结点

    scp -r /usr/app/spark-2.0.0-bin-hadoop2.7 root@hadoop12:/usr/app
    scp -r /usr/app/spark-2.0.0-bin-hadoop2.7 root@hadoop13:/usr/app
  

• 编辑其余两台的环境变量

    export Spark_HOME=/usr/app/spark-2.0.0-bin-hadoop2.7
    export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HBASE_HOME/bin:$Spark_HOME/bin:$S
  

• 启动

    /usr/app/spark-2.0.0-bin-hadoop2.7/sbin/start-all.sh #启动Spark集群
    /usr/app/spark-2.0.0-bin-hadoop2.7/bin/spark-shell  #启动spark-shell