第6课：精通Spark集群搭建与测试

ifuleyou

　　准备3台虚拟机
　　一、安装Linux虚拟机

　　如无特殊说明，以下步骤每台机器上都执行
　　使用ubuntukylin-14.04.2-desktop-amd64安装包，安装ubuntu系统。
　　1.1 为了避免权限问题，启用root用户。
　　参考 http://jingyan.baidu.com/article/148a1921a06bcb4d71c3b1af.html
　　1.2 安装vim
apt-get install vim　　1.3 修改主机名
vi /etc/hostname　　三台机器上分别改为：spark-master、spark-worker1、spark-worker2
　　

　　1.4 修改/etc/hosts文件
192.168.255.129 spark-master
192.168.255.130 spark-worker1
192.168.255.131 spark-worker2　　1.5 安装ssh
root@spark-master:~# apt-get install ssh　　要使root可以使用ssh，作如下修改
vi /etc/ssh/sshd_config
PermitRootLogin without-password   --> 改为 PermitRootLogin yes　　重启机器
　　

　　1.6 配置ssh免密码登陆
root@spark-worker2:~# ssh-keygen -t rsa
Generating public/private rsa key pair.
Enter file in which to save the key (/root/.ssh/id_rsa):
Created directory '/root/.ssh'.
Enter passphrase (empty for no passphrase):
Enter same passphrase again:
Your identification has been saved in /root/.ssh/id_rsa.
Your public key has been saved in /root/.ssh/id_rsa.pub.
The key fingerprint is:
a5:ee:f8:34:be:a2:da:05:f2:20:ae:04:8f:ce:77:b3 root@spark-worker2
The key's randomart image is:
+--[ RSA 2048]----+
|                 |
|                 |
|          .      |
|         o       |
|o o .   S        |
|o+ + . .         |
|.o. . . +        |
|=  o +.= .       |
|.oo.+E+o=.       |
+-----------------+　　复制公钥到master的authorized_keys文件中
root@spark-worker2:~# ssh-copy-id spark-master　　三台都执行完上述操作后，将生成的authorized_keys文件copy到worker1和worker2上
scp authorized_keys spark-worker1:/root/.ssh
scp authorized_keys spark-worker2:/root/.ssh　　

　　

　　二、安装jdk （3台机器）
　　2.1 下载jdk-8u60-linux-x64.tar ，并上传至服务器
root@rich:~/桌面# cd /tools/
root@rich:/tools# ls
jdk-8u60-linux-x64.tar.gz  VMware Tools
root@rich:/tools#
root@rich:/tools#
root@rich:/tools# mkdir /usr/lib/java
root@rich:/tools# tar -zxvf jdk-8u60-linux-x64.tar.gz -C /usr/lib/java/　　2.2 添加环境变量
root@rich:/usr/lib/java# ls
jdk1.8.0_60
root@rich:/usr/lib/java# vi /root/.bashrc　　添加如下内容

export JAVA_HOME=/usr/lib/java/jdk1.8.0_60
export JRE_HOME=$JAVA_HOME/jre/
export CLASS_PATH=$JAVA_HOME/lib:$JRE_HOME/lib
export PATH=$JAVA_HOME/bin　　查看java版本
root@rich:~# java -version
java version "1.8.0_60"
Java(TM) SE Runtime Environment (build 1.8.0_60-b27)
Java HotSpot(TM) 64-Bit Server VM (build 25.60-b23, mixed mode)　　

　　三、 安装hadoop
　　3.1 上传hadoop-2.6.0.tar.gz 至master服务器，加压至/usr/local/hadoop/目录
root@spark-master:/tools# mkdir /usr/local/hadoop
root@spark-master:/tools# tar -zxvf hadoop-2.6.0.tar.gz -C /usr/local/hadoop/　　3.2 配置hadoop集群
　　编辑 core-site.xml
root@spark-master:/usr/local/hadoop/hadoop-2.6.0/etc/hadoop# vi core-site.xml
## 添加如下内容

  
     fs.defaultFS
     hdfs://spark-master
     HDFS文件系统的地址
  
　　

　　编辑 hdfs-site.xml
root@spark-master:/usr/local/hadoop/hadoop-2.6.0/etc/hadoop# vi hdfs-site.xml
#添加如下内容

        
                dfs.namenode.name.dir
                /usr/local/hadoop/hadoop-2.6.0/dns/name
        
        
                dfs.datanode.data.dir
                /usr/local/hadoop/hadoop-2.6.0/dns/data
        
　　编辑mapred-site
root@spark-master:/usr/local/hadoop/hadoop-2.6.0/etc/hadoop# vi mapred-site.xml

        
                mapreduce.framework.name
                yarn
        
　　编辑yarn-site.xml


        
            yarn.resourcemanager.hostname
            spark-master
        
　　编辑hadoop-env.sh
#修改JAVA_HOME的值
export JAVA_HOME=/usr/lib/java/jdk1.8.0_60　　

　　编辑slave文件，添加从节点
root@spark-master:/usr/local/hadoop/hadoop-2.6.0/etc/hadoop# vi slaves
spark-worker1
spark-worker2　　

　　编辑root的.bashrc文件
#添加
export HADOOP_HOME=//usr/local/hadoop/hadoop-2.6.0
export HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop
export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native/
export HADOOP_OPTS="-Djava.library.path=$HADOOP_HOME/lib"
export PATH=$HADOOP_HOME/sbin:$PATH　　

　　3.3 将hadoop安装目录copy到worker1和worker2
root@spark-master:/usr/local# cd /usr/local/
root@spark-master:/usr/local# scp -r hadoop/  spark-worker1:/usr/local/
root@spark-master:/usr/local# scp -r hadoop/  spark-worker2:/usr/local/　　

　　四、启动集群
　　4.1 格式化hdfs
　　因为hdfs是一种文件系统，所以使用之前要对系统进行格式化
root@spark-master:/usr/local/hadoop/hadoop-2.6.0/bin# ./hdfs namenode -format　　

　　4.2 启动dfs
root@spark-master:~# start-dfs.sh
16/02/17 15:38:23 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Starting namenodes on [spark-master]
spark-master: starting namenode, logging to //usr/local/hadoop/hadoop-2.6.0/logs/hadoop-root-namenode-spark-master.out
spark-worker1: starting datanode, logging to //usr/local/hadoop/hadoop-2.6.0/logs/hadoop-root-datanode-spark-worker1.out
spark-worker2: starting datanode, logging to //usr/local/hadoop/hadoop-2.6.0/logs/hadoop-root-datanode-spark-worker2.out
Starting secondary namenodes [0.0.0.0]
0.0.0.0: starting secondarynamenode, logging to //usr/local/hadoop/hadoop-2.6.0/logs/hadoop-root-secondarynamenode-spark-master.out
16/02/17 15:39:36 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
root@spark-master:~# jps
14292 Jps
13995 NameNode
14190 SecondaryNameNoderoot@spark-worker1:/usr/lib/java/jdk1.8.0_60# jps
11465 DataNode
11532 Jpsroot@spark-worker2:~# jps
11282 Jps
11210 DataNode　　

　　4.3 登录web集群管理界面
http://spark-master:50070　　

　　4.4 启动yarn

root@spark-master:~# start-yarn.sh
starting yarn daemons
starting resourcemanager, logging to //usr/local/hadoop/hadoop-2.6.0/logs/yarn-root-resourcemanager-spark-master.out
spark-worker1: starting nodemanager, logging to //usr/local/hadoop/hadoop-2.6.0/logs/yarn-root-nodemanager-spark-worker1.out
spark-worker2: starting nodemanager, logging to //usr/local/hadoop/hadoop-2.6.0/logs/yarn-root-nodemanager-spark-worker2.out
root@spark-master:~# jps
14601 ResourceManager
13995 NameNode
14844 Jps
14190 SecondaryNameNode　　查看yarn的web管理界面
http://spark-master:8088/　　

　　五、安装scala
　　5.1 解压软件
root@spark-master:/tools# cd /tools/
root@spark-master:/tools# mkdir /usr/local/scala ; tar -zxvf scala-2.10.4.tar.gz -C /usr/local/scala/　　5.2 配置环境变量
export SCALA_HOME=/usr/local/scala/scala-2.10.4/
export PATH=$JAVA_HOME/bin:$SCALA_HOME/bin:$PATH　　

　　六、安装spark1.6.0

　　6.1 上传安装包spark-1.6.0-bin-hadoop2.6.gz至master机器
　　解压：
root@spark-master:~# cd /tools/
root@spark-master:/tools# mkdir /usr/local/spark
root@spark-master:/tools# tar -zxvf spark-1.6.0-bin-hadoop2.6.tgz -C /usr/local/spark/　　6.2 配置spark-env.sh

root@spark-master:/tools# cd /usr/local/spark/spark-1.6.0-bin-hadoop2.6/
root@spark-master:/usr/local/spark/spark-1.6.0-bin-hadoop2.6# ls
bin  CHANGES.txt  conf  data  ec2  examples  lib  LICENSE  licenses  NOTICE  python  R  README.md  RELEASE  sbin
root@spark-master:/usr/local/spark/spark-1.6.0-bin-hadoop2.6# cd conf/
root@spark-master:/usr/local/spark/spark-1.6.0-bin-hadoop2.6/conf# ls
docker.properties.template  fairscheduler.xml.template  log4j.properties.template  metrics.properties.template  slaves.template  spark-defaults.conf.template  spark-env.sh.template
root@spark-master:/usr/local/spark/spark-1.6.0-bin-hadoop2.6/conf# cp spark-env.sh.template spark-env.shroot@spark-master:~# cd /usr/local/spark/spark-1.6.0-bin-hadoop2.6/conf/
root@spark-master:/usr/local/spark/spark-1.6.0-bin-hadoop2.6/conf# vi spark-env.sh
#添加如下内容
export JAVA_HOME=/usr/lib/java/jdk1.8.0_60
export SCALA_HOME=/usr/local/scala/scala-2.10.4/
export HADOOP_HOME=/usr/local/hadoop/hadoop-2.6.0
export HADOOP_CONF_DIR=/usr/local/hadoop/hadoop-2.6.0/etc/hadoop
export SPARK_MASTER_IP=spark-master
export SPARK_WORKER_MEMORY=512M
export SPARK_EXECUTOR_MEMORY=512M
export SPARK_DRIVE_MEMORY=512M
export SPARK_WORKER_CORES=8　　6.3 编辑slaves文件
root@spark-master:/usr/local/spark/spark-1.6.0-bin-hadoop2.6/conf# cp slaves.template slaves
root@spark-master:/usr/local/spark/spark-1.6.0-bin-hadoop2.6/conf# vi slaves
##添加所有worker节点
spark-worker1
spark-worker2　　

　　6.4 编辑.bashrc
#添加
export SPARK_HOME=/usr/local/spark/spark-1.6.0-bin-hadoop2.6/　　

　　6.5 将spark目录同步到worker机器上
　　root@spark-master:/usr/local# scp -r spark spark-worker1:/usr/local
　　root@spark-master:/usr/local# scp -r spark spark-worker2:/usr/local
　　

　　6.6 启动spark
root@spark-master:/usr/local/spark/spark-1.6.0-bin-hadoop2.6/sbin# ./start-all.sh
starting org.apache.spark.deploy.master.Master, logging to /usr/local/spark/spark-1.6.0-bin-hadoop2.6/logs/spark-root-org.apache.spark.deploy.master.Master-1-spark-master.out
spark-worker2: starting org.apache.spark.deploy.worker.Worker, logging to /usr/local/spark/spark-1.6.0-bin-hadoop2.6/logs/spark-root-org.apache.spark.deploy.worker.Worker-1-spark-worker2.out
spark-worker1: starting org.apache.spark.deploy.worker.Worker, logging to /usr/local/spark/spark-1.6.0-bin-hadoop2.6/logs/spark-root-org.apache.spark.deploy.worker.Worker-1-spark-worker1.out
root@spark-master:/usr/local/spark/spark-1.6.0-bin-hadoop2.6/sbin#　　6.7 测试
　　启动spark-shell
root@spark-master:/usr/local/spark/spark-1.6.0-bin-hadoop2.6# cd bin/
root@spark-master:/usr/local/spark/spark-1.6.0-bin-hadoop2.6/bin# ./spark-shell　　运行一个简单的wordcount程序

scala> val text_file = sc.textFile("
scala> val counts = text_file.flatMap(line => line.split(" ")).map(word => (word, 1)).reduceByKey(_ + _)
scala> counts.saveAsTextFile("file:///tmp/wordcount")　　查看运行结果
root@spark-master:~# cd /tmp/wordcount/
root@spark-master:/tmp/wordcount# ls
part-00000  _SUCCESS　　part-00000为结果文件，_SUCCESS 为运行状态文件