hadoop实战之分布式模式
环境
192.168.1.101 host101
192.168.1.102 host102
1.安装配置host101
[root@host101 ~]# cat /etc/hosts |grep 192
192.168.1.101 host101
192.168.1.102 host102
[root@host101 ~]# rpm -ivh jdk-8u91-linux-x64.rpm
[root@host101 ~]# tar -zxvf hadoop-2.6.4.tar.gz
[root@host101 ~]# mv hadoop-2.6.4 /usr/local/hadoop
[root@host101 ~]# cd /usr/local/hadoop/
[root@host101 hadoop]# vim etc/hadoop/hadoop-env.sh
export JAVA_HOME=/usr/java/latest
export HADOOP_PREFIX=/usr/local/hadoop
[root@host101 hadoop]# vim etc/hadoop/slaves
host101
host102
[root@host101 hadoop]# vim etc/hadoop/core-site.xml
<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://host101:9000</value>
</property>
</configuration> [root@host101 hadoop]# mkdir -p /hadoop/
[root@host101 hadoop]# vim etc/hadoop/hdfs-site.xml
<configuration>
<property>
<name>dfs.replication</name>
<value>1</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>/hadoop/name/</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>/hadoop/data/</value>
</property>
</configuration>
[root@host101 hadoop]# vim mapred-site.xml
<configuration>
<property>
<name>mapred.job.tracker</name>
<value>host101:9001</value>
</property>
</configuration>
[root@host101 ~]# ssh-keygen
[root@host101 ~]# ssh-copy-id host101
[root@host101 ~]# ssh-copy-id host102
2.安装配置host102
[root@host102 ~]# scp host101:/root/hadoop-2.6.4.tar.gz .
[root@host102 ~]# scp host101:/root/jdk-8u91-linux-x64.rpm . [root@host102 ~]# rpm -ivh jdk-8u91-linux-x64.rpm
[root@host102 ~]# tar -zxvf hadoop-2.6.4.tar.gz
[root@host102 ~]# mv hadoop-2.6.4 /usr/local/hadoop
[root@host102 ~]# ssh-keygen
[root@host102 ~]# ssh-copy-id host101
[root@host102 ~]# ssh-copy-id host102
[root@host102 etc]# cd /usr/local/hadoop/etc/hadoop/
[root@host102 hadoop]# scp host101:/usr/local/hadoop/etc/hadoop/mapred-site.xml .
[root@host102 hadoop]# scp host101:/usr/local/hadoop/etc/hadoop/slaves .
[root@host102 hadoop]# scp host101:/usr/local/hadoop/etc/hadoop/hdfs-site.xml .
[root@host102 hadoop]# scp host101:/usr/local/hadoop/etc/hadoop/hadoop-env.sh .
[root@host102 hadoop]# scp host101:/usr/local/hadoop/etc/hadoop/core-site.xml .
3.启动hadoop集群
[root@host101 hadoop]# sbin/start-all.sh
This script is Deprecated. Instead use start-dfs.sh and start-yarn.sh
Starting namenodes on [host101]
host101: starting namenode, logging to /usr/local/hadoop/logs/hadoop-root-namenode-host101.out
host101: starting datanode, logging to /usr/local/hadoop/logs/hadoop-root-datanode-host101.out
host102: starting datanode, logging to /usr/local/hadoop/logs/hadoop-root-datanode-host102.out
Starting secondary namenodes [0.0.0.0]
0.0.0.0: starting secondarynamenode, logging to /usr/local/hadoop/logs/hadoop-root-secondarynamenode-host101.out
starting yarn daemons
starting resourcemanager, logging to /usr/local/hadoop/logs/yarn-root-resourcemanager-host101.out
host101: starting nodemanager, logging to /usr/local/hadoop/logs/yarn-root-nodemanager-host101.out
host102: starting nodemanager, logging to /usr/local/hadoop/logs/yarn-root-nodemanager-host102.out [root@host101 hadoop]# bin/hdfs dfs -mkdir /eric
[root@host101 hadoop]# bin/hdfs dfs -ls /
Found 1 items
drwxr-xr-x - root supergroup 0 2016-07-06 12:09 /eric
[root@host101 hadoop]# bin/hadoop dfsadmin -report
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it. Configured Capacity: 37576769536 (35.00 GB)
Present Capacity: 29447094272 (27.42 GB)
DFS Remaining: 29447086080 (27.42 GB)
DFS Used: 8192 (8 KB)
DFS Used%: 0.00%
Under replicated blocks: 0
Blocks with corrupt replicas: 0
Missing blocks: 0 -------------------------------------------------
Live datanodes (2): Name: 192.168.1.101:50010 (host101)
Hostname: host101
Decommission Status : Normal
Configured Capacity: 18788384768 (17.50 GB)
DFS Used: 4096 (4 KB)
Non DFS Used: 3870842880 (3.61 GB)
DFS Remaining: 14917537792 (13.89 GB)
DFS Used%: 0.00%
DFS Remaining%: 79.40%
Configured Cache Capacity: 0 (0 B)
Cache Used: 0 (0 B)
Cache Remaining: 0 (0 B)
Cache Used%: 100.00%
Cache Remaining%: 0.00%
Xceivers: 1
Last contact: Wed Jul 06 12:10:07 CST 2016 Name: 192.168.1.102:50010 (host102)
Hostname: host102
Decommission Status : Normal
Configured Capacity: 18788384768 (17.50 GB)
DFS Used: 4096 (4 KB)
Non DFS Used: 4258832384 (3.97 GB)
DFS Remaining: 14529548288 (13.53 GB)
DFS Used%: 0.00%
DFS Remaining%: 77.33%
Configured Cache Capacity: 0 (0 B)
Cache Used: 0 (0 B)
Cache Remaining: 0 (0 B)
Cache Used%: 100.00%
Cache Remaining%: 0.00%
Xceivers: 1
Last contact: Wed Jul 06 12:10:07 CST 2016
[root@host101 hadoop]# jps
3920 DataNode
3811 NameNode
4056 SecondaryNameNode
4299 Jps
4. 测试集群
NameNode http://192.168.1.101:50070/dfshealth.html
ResourceManager http://192.168.1.101:8088/cluster
http://192.168.1.101:8042/node [root@host101 hadoop]# bin/hadoop fs -mkdir /eric/input
[root@host101 hadoop]# bin/hadoop fs -copyFromLocal etc/hadoop/*.xml /eric/input
[root@host101 hadoop]# bin/hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-2.6.4.jar grep /eric/input /eric/output 'dfs[a-z.]+'
[root@host101 hadoop]# bin/hadoop fs -ls /eric/output/
Found 2 items
-rw-r--r-- 1 root supergroup 0 2016-07-06 12:38 /eric/output/_SUCCESS
-rw-r--r-- 1 root supergroup 77 2016-07-06 12:38 /eric/output/part-r-00000
[root@host101 hadoop]# bin/hadoop fs -cat /eric/output/part-r-00000
1 dfsadmin
1 dfs.replication
1 dfs.namenode.name.dir
1 dfs.datanode.data.dir
[root@host101 hadoop]# sbin/stop-all.sh
This script is Deprecated. Instead use stop-dfs.sh and stop-yarn.sh
Stopping namenodes on [host101]
host101: stopping namenode
host101: stopping datanode
host102: stopping datanode
Stopping secondary namenodes [0.0.0.0]
0.0.0.0: stopping secondarynamenode
stopping yarn daemons
stopping resourcemanager
host101: stopping nodemanager
host102: no nodemanager to stop
no proxyserver to stop
5. 动态添加节点
[root@host101 hadoop]# echo "192.168.1.161 host161" >> /etc/hosts
[root@host102 hadoop]# echo "192.168.1.161 host161" >> /etc/hosts
[root@host101 hadoop]# ssh-copy-id host161
[root@host102 hadoop]# ssh-copy-id host161
[root@host161 ~]# ssh-copy-id host161
[root@host161 ~]# ssh-copy-id host101
[root@host161 ~]# ssh-copy-id host102
[root@host102 ~]# scp host101:/root/hadoop-2.6.4.tar.gz .
[root@host102 ~]# scp host101:/root/jdk-8u91-linux-x64.rpm .
[root@host102 ~]# rpm -ivh jdk-8u91-linux-x64.rpm
[root@host102 ~]# tar -zxvf hadoop-2.6.4.tar.gz
[root@host102 ~]# mv hadoop-2.6.4 /usr/local/hadoop
[root@host101 hadoop]# echo 'host161' >> etc/hadoop/slaves
[root@host102 hadoop]# echo 'host161' >> etc/hadoop/slaves
[root@host161 hadoop]# scp host101:/usr/local/hadoop/etc/hadoop/mapred-site.xml .
[root@host161 hadoop]# scp host101:/usr/local/hadoop/etc/hadoop/slaves .
[root@host161 hadoop]# scp host101:/usr/local/hadoop/etc/hadoop/hdfs-site.xml .
[root@host161 hadoop]# scp host101:/usr/local/hadoop/etc/hadoop/hadoop-env.sh .
[root@host161 hadoop]# scp host101:/usr/local/hadoop/etc/hadoop/core-site.xml .
[root@host161 hadoop]# sbin/hadoop-daemon.sh start datanode
starting datanode, logging to /usr/local/hadoop/logs/hadoop-root-datanode-host161.out [root@host101 hadoop]# bin/hadoop dfsadmin -report
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it. Configured Capacity: 56365154304 (52.49 GB)
Present Capacity: 44354347008 (41.31 GB)
DFS Remaining: 44192788480 (41.16 GB)
DFS Used: 161558528 (154.07 MB)
DFS Used%: 0.36%
Under replicated blocks: 0
Blocks with corrupt replicas: 0
Missing blocks: 0 -------------------------------------------------
Live datanodes (3): Name: 192.168.1.101:50010 (host101)
Hostname: host101
Decommission Status : Normal
Configured Capacity: 18788384768 (17.50 GB)
DFS Used: 161546240 (154.06 MB)
Non DFS Used: 3873861632 (3.61 GB)
DFS Remaining: 14752976896 (13.74 GB)
DFS Used%: 0.86%
DFS Remaining%: 78.52%
Configured Cache Capacity: 0 (0 B)
Cache Used: 0 (0 B)
Cache Remaining: 0 (0 B)
Cache Used%: 100.00%
Cache Remaining%: 0.00%
Xceivers: 1
Last contact: Wed Jul 06 16:02:19 CST 2016 Name: 192.168.1.161:50010 (host161)
Hostname: host161
Decommission Status : Normal
Configured Capacity: 18788384768 (17.50 GB)
DFS Used: 4096 (4 KB)
Non DFS Used: 3877494784 (3.61 GB)
DFS Remaining: 14910885888 (13.89 GB)
DFS Used%: 0.00%
DFS Remaining%: 79.36%
Configured Cache Capacity: 0 (0 B)
Cache Used: 0 (0 B)
Cache Remaining: 0 (0 B)
Cache Used%: 100.00%
Cache Remaining%: 0.00%
Xceivers: 1
Last contact: Wed Jul 06 16:02:20 CST 2016 Name: 192.168.1.102:50010 (host102)
Hostname: host102
Decommission Status : Normal
Configured Capacity: 18788384768 (17.50 GB)
DFS Used: 8192 (8 KB)
Non DFS Used: 4259450880 (3.97 GB)
DFS Remaining: 14528925696 (13.53 GB)
DFS Used%: 0.00%
DFS Remaining%: 77.33%
Configured Cache Capacity: 0 (0 B)
Cache Used: 0 (0 B)
Cache Remaining: 0 (0 B)
Cache Used%: 100.00%
Cache Remaining%: 0.00%
Xceivers: 1
Last contact: Wed Jul 06 16:02:19 CST 2016
hadoop实战之分布式模式的更多相关文章
- Hadoop基础-完全分布式模式部署yarn日志聚集功能
Hadoop基础-完全分布式模式部署yarn日志聚集功能 作者:尹正杰 版权声明:原创作品,谢绝转载!否则将追究法律责任. 其实我们不用配置也可以在服务器后台通过命令行的形式查看相应的日志,但为了更方 ...
- Hadoop三种安装模式：单机模式，伪分布式，真正分布式
Hadoop三种安装模式:单机模式,伪分布式,真正分布式 一 单机模式standalone单 机模式是Hadoop的默认模式.当首次解压Hadoop的源码包时,Hadoop无法了解硬件安装环境,便保守 ...
- 王家林的“云计算分布式大数据Hadoop实战高手之路---从零开始”的第十一讲Hadoop图文训练课程：MapReduce的原理机制和流程图剖析
这一讲我们主要剖析MapReduce的原理机制和流程. “云计算分布式大数据Hadoop实战高手之路”之完整发布目录 云计算分布式大数据实战技术Hadoop交流群:312494188,每天都会在群中发 ...
- 云计算分布式大数据Hadoop实战高手之路第七讲Hadoop图文训练课程：通过HDFS的心跳来测试replication具体的工作机制和流程
这一讲主要深入使用HDFS命令行工具操作Hadoop分布式集群,主要是通过实验的配置hdfs-site.xml文件的心跳来测试replication具体的工作和流程. 通过HDFS的心跳来测试repl ...
- 云计算分布式大数据Hadoop实战高手之路第八讲Hadoop图文训练课程：Hadoop文件系统的操作实战
本讲通过实验的方式讲解Hadoop文件系统的操作. “云计算分布式大数据Hadoop实战高手之路”之完整发布目录 云计算分布式大数据实战技术Hadoop交流群:312494188,每天都会在群中发布云 ...
- Hadoop伪分布式模式部署
Hadoop的安装有三种执行模式: 单机模式(Local (Standalone) Mode):Hadoop的默认模式,0配置.Hadoop执行在一个Java进程中.使用本地文件系统.不使用HDFS, ...
- hadoop的安装和配置（三）完全分布式模式
博主会用三篇文章为大家详细说明hadoop的三种模式: 本地模式 伪分布模式 完全分布模式 完全分布式模式: 前面已经说了本地模式和伪分布模式,这两种在hadoop的应用中并不用于实际,因为几乎没人会 ...
- 使用docker搭建hadoop环境，并配置伪分布式模式
docker 1.下载docker镜像 docker pull registry.cn-hangzhou.aliyuncs.com/kaibb/hadoop:latest 注:此镜像为阿里云个人上传镜 ...
- Hadoop Single Node Setup（hadoop本地模式和伪分布式模式安装-官方文档翻译 2.7.3）
Purpose(目标) This document describes how to set up and configure a single-node Hadoop installation so ...
随机推荐
- Eclipse中Java项目转换为Web项目
刚创建完的Java Project是这样的 右键项目名,找到这个地方 修改下方的 Default output folder 为 Vehicle-Report/WebContent/WEB-INF/c ...
- 日期转换时Safari中返回Invalid Date
问题: 进行日期转换时,Safari中会返回Invalid Date, 而IE 9, Firefox, Chrome and Opera显示正常,代码如下所示: var d = new Date(&q ...
- SSM框架学习之高并发秒杀业务--笔记1-- 项目的创建和依赖
在慕课网上看了Java高并发秒杀API视屏后,觉得这个案例真的让我学到了很多,现在重新自己实现一遍,博客记下,顺便分析其中的要点. 第一步是项目的创建和依赖 利用Maven去创建工程然后导入Idea中 ...
- Octopus系列之UploadValues异步上载
不多说了直接上代码 public void ProcessRequest(HttpContext context) { context.Response.ContentType = "tex ...
- PostgreSQL 列出所有表名和数据库名
列出表名 直接 \d 不加参数 或 SELECT tablename FROM pg_tables WHERE tablename NOT LIKE 'pg%' ...
- C#/ASP.NET MVC微信公众号接口开发之从零开发（二） 接收微信消息并且解析XML(附源码)
文章导读: C#微信公众号接口开发之从零开发(一) 接入微信公众平台 微信接入之后,微信通过我们接入的地址进行通信,其中的原理是微信用户发送消息给微信公众账号,微信服务器将消息以xml的形式发送到我们 ...
- Josephu--Java链表实现
public class Josephu { public static void main(String[] args) { Cyclink cyclink=new Cyclink(); cycli ...
- MyEclipse中Maven的配置
之前在MyEclipse这个IDE中配置Maven,完成配置后启动Maven时出现-Dmaven.multiModuleProjectDirectory system propery is not s ...
- c#基础知识-2
1.在控制台接受数据时可以这样输入: using System; using System.Collections.Generic; using System.Linq; using System.T ...
- Android 计算器UI-TableLayout
表格布局(TableLayout) <?xml version="1.0" encoding="utf-8"?> <TableLayout x ...