Spark安装部署

一 下载Scala和Spark

[root@master opt]# wget http://downloads.lightbend.com/scala/2.11.8/scala-2.11.8.tgz
[root@master opt]# wget http://d3kbcqa49mib13.cloudfront.net/spark-2.0.0-bin-hadoop2.7.tgz

二 安装Scala

1 解压

[root@master opt]# tar -zxvf scala-2.11.8.tgz

2 配置环境变量

export SCALA_HOME=/opt/scala-2.11.8
export PATH=$PATH:$SCALA_HOME/bin

3 测试

[root@master opt]# scala
Welcome to Scala 2.11.8 (Java HotSpot(TM) 64-Bit Server VM, Java 1.8.0_152).
Type in expressions for evaluation. Or try :help.
scala>

三 安装Spark

1 解压

[root@master opt]# tar -zxvf spark-2.0.0-bin-hadoop2.7.tgz

2 配置环境变量

export SPARK_HOME=/opt/spark-2.0.0-bin-hadoop2.7
export PATH=$PATH:$SPARK_HOME/bin

3 配置spark-env.sh

export JAVA_HOME=/opt/jdk1.8
export PATH=$PATH:$JAVA_HOME/bin
export SCALA_HOME=/opt/scala-2.11.8
export PATH=$PATH:$SCALA_HOME/bin
export SPARK_HOME=/opt/spark-2.0.0-bin-hadoop2.7
export PATH=$PATH:$SPARK_HOME/bin

四 启动

[root@master sbin]# ./start-all.sh
starting org.apache.spark.deploy.master.Master, logging to /opt/spark-2.0.0-bin-hadoop2.7/logs/spark-root-org.apache.spark.deploy.master.Master-1-master.out
localhost: \S
localhost: Kernel \r on an \m
localhost: starting org.apache.spark.deploy.worker.Worker, logging to /opt/spark-2.0.0-bin-hadoop2.7/logs/spark-root-org.apache.spark.deploy.worker.Worker-1-master.out
[root@master sbin]# jps
4128 Jps
4049 Worker
3992 Master

五 测试

[root@master ~]# cat test.log
hello go
java
c mysql
[root@master sbin]# spark-shell
Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties
Setting default log level to "WARN".
To adjust logging level use sc.setLogLevel(newLevel).
18/02/03 22:25:05 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
18/02/03 22:25:08 WARN SparkContext: Use an existing SparkContext, some configuration may not take effect.
Spark context Web UI available at http://192.168.0.110:4040
Spark context available as 'sc' (master = local[*], app id = local-1517667907847).
Spark session available as 'spark'.
Welcome to
      ____              __
     / __/__  ___ _____/ /__
    _\ \/ _ \/ _ `/ __/  '_/
   /___/ .__/\_,_/_/ /_/\_\   version 2.0.0
      /_/
         
Using Scala version 2.11.8 (Java HotSpot(TM) 64-Bit Server VM, Java 1.8.0_152)
Type in expressions to have them evaluated.
Type :help for more information.
scala> var file = sc.textFile("/root/test.log");
file: org.apache.spark.rdd.RDD[String] = /root/test.log MapPartitionsRDD[1] at textFile at <console>:24
scala> file.collect
res1: Array[String] = Array(hello go, java, c mysql, "", "")
scala> var file = sc.textFile("hdfs://master/test.log");
file: org.apache.spark.rdd.RDD[String] = hdfs://master/test.log MapPartitionsRDD[3] at textFile at <console>:24
scala> file.collect
res2: Array[String] = Array(hello go, java, c mysql, "", "")