hadoop入门

1.事先准备好一台linux虚拟机（网卡为仅主机模式，最小化安装）

#systemctl stop firewalld      //关闭防火墙
#systemctl disable firewalld      //防止开机自启

2.IPADDR 192.168.56.100/24 网关192.168.56.1

#vi /etc/sysconfig/network 
NETWORKING=yes
GATEWAY=192.168.56.1
#vi /etc/sysconfig/network-sripts/ifcfg-enp0s3
TYPE=Ethernet 
IPADDR=192.168.56.100 
NETMASK=255.255.255.0

3.用root连接Xshell，使用xftp上传jdk和hadoop
4.安装jdk和hadoop（检验是否成功）

#cd /usr/local
#rpm -ivh jkd-8u91-linux-64.rpm   //用Tab补齐
#cd /usr/
#java
#cd local
#ls
#tar -xvf hadoop-2.7.3.tar.gz   //注意用Tab补齐

#cd /usr/local
#ls
bin  games   hadoop-2.7.3.tar.gz  jdk-8u91-linux-x64.rpm  lib64    sbin   src
etc  hadoop  include              lib                     libexec  share
# cd hadoop
# cd etc
# ls
hadoop
# cd h*
# ls
capacity-scheduler.xml      httpfs-env.sh            mapred-env.sh
configuration.xsl           httpfs-log4j.properties  mapred-queues.xml.template
container-executor.cfg      httpfs-signature.secret  mapred-site.xml.template
core-site.xml               httpfs-site.xml          slaves
hadoop-env.cmd              kms-acls.xml             ssl-client.xml.example
hadoop-env.sh               kms-env.sh               ssl-server.xml.example
hadoop-metrics2.properties  kms-log4j.properties     yarn-env.cmd
hadoop-metrics.properties   kms-site.xml             yarn-env.sh
hadoop-policy.xml           log4j.properties         yarn-site.xml
hdfs-site.xml               mapred-env.cmd
#vim hadoop-env.sh   //配置hadoop环境
//将export JAVA_HOME=${JAVA_HOME}改写为export JAVA_HOME=/usr/java/default
#vim /etc/profile
//zai 末尾添加export PATH=$PATH:/usr/local/hadoop/bin:/usr/local/hadoop/sbin
#source /etc/profile   //执行改写的文件，使之生效
#hadoop

5.退出master，将master复制三台服务器：slave1，slave2，slave3
6.将三台服务器的Ip分别改为192.168.56.101，192.168.56.102，192.168.56.103，名字分别为slave1，slave2，slave3
查看是否都能ping通

systemctl stop firewalld   //关闭防火墙
systemctl disable firewalld   //关闭开机自启

7.master管理者另外三台服务器（slave1,2,3）（工具--发送键送到所以会话）

#cd /usr/local/hadoop/etc/hadoop
#vim core-site.xml    //四台都要


    fs.defaultFS   //名字
    hdfs://master:9000   //hdfs协议，9000为监听端口

   
#vim /etc/hosts
192.168.56.100 master
192.168.56.101 slave1
192.168.56.102 slave2
192.168.56.103 slave3

//在master中
#hdfs namenode .format    //格式化
#hadoop-daemon.sh start namenode
starting namenode, logging to /usr/local/ha
# jps
3352 NameNode       //成功
3420 Jps  
    
//在slave1,2,3中
#hadoop-daemo.sh start datanode
starting datanode, logging to /usr/local/hadoop/logs/hadoop-root-datanode-slave1.out
#jps
3210 DataNode           //成功
3293 Jps

8.开启关闭集群命令

#hadoop-daemon.sh stop namenode   //关闭
#hadoop-daemon.sh start namenode   //开启
#jps  //用来观察进程情况

9.集中式管理添加所有机器

#vim slaves
slave1
slave2
slave3
#start-dfs.sh  //启动所有机器（需要输入密码）
#jps

10.ssh免密登录

#ssh slave1     //第一次需要输入密码
#exit
#cd    //进入根目录
#ls -la
#cd .ssh
#ssh-keygen -t rsa    //默认直接回车确认
#ls
id_rsa  id_rsa.pub  known_hosts    //id_rsa是root的私钥，id_rsa.pub是root的公钥
#ssh-copy-id slave1  //传递公钥
#ssh-copy-id slave2
#ssh-copy-id slave3
#ssh-copy-id master  //默认本机也是远程登录，所以也需要
stop-dfs.sh //关闭集群
start-dfs.sh //开启集群

11.上传一个文件，每个hdfs块文件备份2份，从节点的心跳检查时间间隔10秒

#ls
capacity-scheduler.xml      httpfs-env.sh            mapred-env.sh
configuration.xsl           httpfs-log4j.properties  mapred-queues.xml.template
container-executor.cfg      httpfs-signature.secret  mapred-site.xml.template
core-site.xml               httpfs-site.xml          slave
hadoop-env.cmd              kms-acls.xml             slaves
hadoop-env.sh               kms-env.sh               ssl-client.xml.example
hadoop-metrics2.properties  kms-log4j.properties     ssl-server.xml.example
hadoop-metrics.properties   kms-site.xml             yarn-env.cmd
hadoop-policy.xml           log4j.properties         yarn-env.sh
hdfs-site.xml               mapred-env.cmd           yarn-site.xml
#vim hdfs-site.xml     //修改多少个备份

dfs.replication
2

# vim hdfs-site.xml

dfs.namenode.heartbeat.recheck-interval
10000   //每隔10000毫秒更新

#cd /usr/local
# ls
bin     hadoop-2.7.3.tar.gz     lib64    src
etc     include                 libexec
games   jdk-8u91-linux-x64.rpm  sbin
hadoop  lib                     share
# hadoop fs -put jdk-8u91-linux-x64.rpm /

12.hadoop.tmp.dir配置为/var/tmphadoop/
1.所有机器都要修改

#cd /tmp
#cd /usr/local/hadoop/etc/hadoop
#ls
#vim core-site.xml

    hadoop.tmp.dir
    /var/hadoop

2.namenode格式化

#hdfs namenode -format
#stop-dfs.sh
#start-dfs.sh

13.进入java配置
1.导入必要的包，新建class
(1).share--hadoop--common--hadoop-common-2.7.3jar
(2).share--hadoop--common--lib--全部
(3).share--hadoop--hdfs--hadoop-hdfs-2.7.3jar
2.新建文件

#cd
#vi hello.test
hello bj
hello sh
hello sz
hello AMD690G
#hadoop fs -put ./hello.txt /
# hadoop fs -ls /
Found 1 items
-rw-r--r--   2 root supergroup         41 2017-10-06 23:12 /hello.txt
#vim hdfs-site.xml

    dfs.permissions.enabled
    false

#stop-dfs.sh
#start-dfs.sh

全部代码

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

public class hellohdfs2 {

    public static void main(String[] args) throws Exception{
        /*URL url = new URL("http://www.baidu.com");
        InputStream in = url.openStream();
        IOUtils.copyBytes(in, System.out , 4096, true);*/
        
        /*URL.setURLStreamHandlerFactory(new FsUrlStreamHandlerFactory());
        URL url = new URL("hdfs://192.168.56.10:9000/hello.txt");
        InputStream in = url.openStream();
        IOUtils.copyBytes(in, System.out , 4096, true);*/
        
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS", "hdfs://192.168.56.10:9000");
        FileSystem fileSystem = FileSystem.get(conf);
        
        /*boolean success = fileSystem.mkdirs(new Path("/msb"));
        System.out.println(success);
        
        success = fileSystem.exists(new Path("/hello.txt"));
        System.out.println(success);  //判断文件是否存在
        
        success = fileSystem.delete(new Path("/msb"), true);
        System.out.println(success);  //删除目录
        
        success = fileSystem.exists(new Path("/msb"));
        System.out.println(success);*/   
        
        /*FSDataOutputStream out = fileSystem.create(new Path("/test.data"), true);
        FileInputStream fis = new FileInputStream("c:/test/core-site.xml");
        IOUtils.copyBytes(fis, out, 4096, true);*/
        
        /*FSDataOutputStream out = fileSystem.create(new Path("/test.data"), true);
        FileInputStream in = new FileInputStream("c:/test/core-site.xml");
        byte[] buf = new byte[4096];
        int len = in.read(buf);
        while(len !=-1) {
            out.write(buf, 0, len);
            len = in.read(buf);
        }
        in.close();
        out.close();*/
        
        FileStatus[] statuses = fileSystem.listStatus(new Path("/"));
        //System.out.println(statuses.length);
        for(FileStatus status : statuses) {
            System.out.println(status.getPath());
            System.out.println(status.getPermission());
            System.out.println(status.getReplication());
        }
    }

}

13.yarn

#cd /usr/local/hadoop/etc/hadoop
#vim yarn-site.xml    //四台都要

    yarn.resourcemanager.hostname
    master

 
  
    yarn.nodemanager.aux-services  
    mapreduce_shuffle  
  
 

    yarn.nodemanager.auxservices.mapreduce.shuffle.class
    org.apache.hadoop.mapred.ShuffleHandler



//namenode上配置mapred-site.xml(要复制)
#vi mapred-site.xml

    mapreduce.framework.name
    yarn



#start-yarn.sh
#jps
8225 NameNode
8418 SecondaryNameNode
8870 ResourceManager
9134 Jps
#vim mapred-site.xml

    mapreduce.framework.name
    yarn

#vi input.txt
hello java
hello java
hello c
hello c++
hello python
hello java
#cd 
# vi input.txt
# hadoop fs -mkdir /wcinput
# hadoop fs -put input.txt /wcinput/
# hadoop fs -ls /wcinput
Found 1 items
-rw-r--r--   2 root supergroup         64 2017-10-07 00:22 /wcinput/input.txt
#find /usr/local/hadoop -name *example*.jar      //查找示例文件
#hadoop jar /usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.7.3.jar wordcount /wcinput/input.txt /wcoutput

通过网页来观察该job的运行情况
192.168.56.10:8088