﻿<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:trackback="http://madskills.com/public/xml/rss/module/trackback/" xmlns:wfw="http://wellformedweb.org/CommentAPI/" xmlns:slash="http://purl.org/rss/1.0/modules/slash/"><channel><title>C++博客-herb-随笔分类-Hadoop</title><link>http://www.cppblog.com/herb/category/15522.html</link><description>我要靠谱→hello world!</description><language>zh-cn</language><lastBuildDate>Sat, 22 Jan 2011 19:05:30 GMT</lastBuildDate><pubDate>Sat, 22 Jan 2011 19:05:30 GMT</pubDate><ttl>60</ttl><item><title>HDFS简介</title><link>http://www.cppblog.com/herb/archive/2011/01/10/138235.html</link><dc:creator>herb</dc:creator><author>herb</author><pubDate>Mon, 10 Jan 2011 01:57:00 GMT</pubDate><guid>http://www.cppblog.com/herb/archive/2011/01/10/138235.html</guid><wfw:comment>http://www.cppblog.com/herb/comments/138235.html</wfw:comment><comments>http://www.cppblog.com/herb/archive/2011/01/10/138235.html#Feedback</comments><slash:comments>0</slash:comments><wfw:commentRss>http://www.cppblog.com/herb/comments/commentRss/138235.html</wfw:commentRss><trackback:ping>http://www.cppblog.com/herb/services/trackbacks/138235.html</trackback:ping><description><![CDATA[&nbsp;&nbsp;&nbsp;&nbsp; 摘要: HDFS全称是Hadoop Distributed System。HDFS是为以流的方式存取大文件而设计的。适用于几百MB，GB以及TB，并写一次读多次的场合。而对于低延时数据访问、大量小文件、同时写和任意的文件修改，则并不是十分适合。<br><br>目前HDFS支持的使用接口除了Java的还有，Thrift、C、FUSE、WebDAV、HTTP等。HDFS是以block-sized chunk组织其文件内容的，默认的block大小为64MB，对于不足64MB的文件，其会占用一个block，但实际上不用占用实际硬盘上的64MB，这可以说是HDFS是在文件系统之上架设的一个中间层。之所以将默认的block大小设置为64MB这么大，是因为block-sized对于文件定位很有帮助，同时大文件更使传输的时间远大于文件寻找的时间，这样可以最大化地减少文件定位的时间在整个文件获取总时间中的比例 。<br><br>&nbsp;&nbsp;<a href='http://www.cppblog.com/herb/archive/2011/01/10/138235.html'>阅读全文</a><img src ="http://www.cppblog.com/herb/aggbug/138235.html" width = "1" height = "1" /><br><br><div align=right><a style="text-decoration:none;" href="http://www.cppblog.com/herb/" target="_blank">herb</a> 2011-01-10 09:57 <a href="http://www.cppblog.com/herb/archive/2011/01/10/138235.html#Feedback" target="_blank" style="text-decoration:none;">发表评论</a></div>]]></description></item><item><title>hadoop二次排序中对组合键，分区，分组的一点应用</title><link>http://www.cppblog.com/herb/archive/2010/12/08/135785.html</link><dc:creator>herb</dc:creator><author>herb</author><pubDate>Wed, 08 Dec 2010 03:13:00 GMT</pubDate><guid>http://www.cppblog.com/herb/archive/2010/12/08/135785.html</guid><wfw:comment>http://www.cppblog.com/herb/comments/135785.html</wfw:comment><comments>http://www.cppblog.com/herb/archive/2010/12/08/135785.html#Feedback</comments><slash:comments>0</slash:comments><wfw:commentRss>http://www.cppblog.com/herb/comments/commentRss/135785.html</wfw:commentRss><trackback:ping>http://www.cppblog.com/herb/services/trackbacks/135785.html</trackback:ping><description><![CDATA[&nbsp;&nbsp;&nbsp;&nbsp; 摘要: &nbsp;&nbsp;<a href='http://www.cppblog.com/herb/archive/2010/12/08/135785.html'>阅读全文</a><img src ="http://www.cppblog.com/herb/aggbug/135785.html" width = "1" height = "1" /><br><br><div align=right><a style="text-decoration:none;" href="http://www.cppblog.com/herb/" target="_blank">herb</a> 2010-12-08 11:13 <a href="http://www.cppblog.com/herb/archive/2010/12/08/135785.html#Feedback" target="_blank" style="text-decoration:none;">发表评论</a></div>]]></description></item><item><title>[转载]用 Hadoop 进行分布式并行编程(三)</title><link>http://www.cppblog.com/herb/archive/2010/11/24/134504.html</link><dc:creator>herb</dc:creator><author>herb</author><pubDate>Wed, 24 Nov 2010 05:52:00 GMT</pubDate><guid>http://www.cppblog.com/herb/archive/2010/11/24/134504.html</guid><wfw:comment>http://www.cppblog.com/herb/comments/134504.html</wfw:comment><comments>http://www.cppblog.com/herb/archive/2010/11/24/134504.html#Feedback</comments><slash:comments>0</slash:comments><wfw:commentRss>http://www.cppblog.com/herb/comments/commentRss/134504.html</wfw:commentRss><trackback:ping>http://www.cppblog.com/herb/services/trackbacks/134504.html</trackback:ping><description><![CDATA[&nbsp;&nbsp;&nbsp;&nbsp; 摘要: &nbsp;&nbsp;<a href='http://www.cppblog.com/herb/archive/2010/11/24/134504.html'>阅读全文</a><img src ="http://www.cppblog.com/herb/aggbug/134504.html" width = "1" height = "1" /><br><br><div align=right><a style="text-decoration:none;" href="http://www.cppblog.com/herb/" target="_blank">herb</a> 2010-11-24 13:52 <a href="http://www.cppblog.com/herb/archive/2010/11/24/134504.html#Feedback" target="_blank" style="text-decoration:none;">发表评论</a></div>]]></description></item><item><title>[转载]用 Hadoop 进行分布式并行编程(二)</title><link>http://www.cppblog.com/herb/archive/2010/11/24/134503.html</link><dc:creator>herb</dc:creator><author>herb</author><pubDate>Wed, 24 Nov 2010 05:51:00 GMT</pubDate><guid>http://www.cppblog.com/herb/archive/2010/11/24/134503.html</guid><wfw:comment>http://www.cppblog.com/herb/comments/134503.html</wfw:comment><comments>http://www.cppblog.com/herb/archive/2010/11/24/134503.html#Feedback</comments><slash:comments>0</slash:comments><wfw:commentRss>http://www.cppblog.com/herb/comments/commentRss/134503.html</wfw:commentRss><trackback:ping>http://www.cppblog.com/herb/services/trackbacks/134503.html</trackback:ping><description><![CDATA[&nbsp;&nbsp;&nbsp;&nbsp; 摘要: &nbsp;&nbsp;<a href='http://www.cppblog.com/herb/archive/2010/11/24/134503.html'>阅读全文</a><img src ="http://www.cppblog.com/herb/aggbug/134503.html" width = "1" height = "1" /><br><br><div align=right><a style="text-decoration:none;" href="http://www.cppblog.com/herb/" target="_blank">herb</a> 2010-11-24 13:51 <a href="http://www.cppblog.com/herb/archive/2010/11/24/134503.html#Feedback" target="_blank" style="text-decoration:none;">发表评论</a></div>]]></description></item><item><title>[转载]用Hadoop进行分布式并行编程(一)</title><link>http://www.cppblog.com/herb/archive/2010/11/24/134502.html</link><dc:creator>herb</dc:creator><author>herb</author><pubDate>Wed, 24 Nov 2010 05:50:00 GMT</pubDate><guid>http://www.cppblog.com/herb/archive/2010/11/24/134502.html</guid><wfw:comment>http://www.cppblog.com/herb/comments/134502.html</wfw:comment><comments>http://www.cppblog.com/herb/archive/2010/11/24/134502.html#Feedback</comments><slash:comments>0</slash:comments><wfw:commentRss>http://www.cppblog.com/herb/comments/commentRss/134502.html</wfw:commentRss><trackback:ping>http://www.cppblog.com/herb/services/trackbacks/134502.html</trackback:ping><description><![CDATA[&nbsp;&nbsp;&nbsp;&nbsp; 摘要: &nbsp;&nbsp;<a href='http://www.cppblog.com/herb/archive/2010/11/24/134502.html'>阅读全文</a><img src ="http://www.cppblog.com/herb/aggbug/134502.html" width = "1" height = "1" /><br><br><div align=right><a style="text-decoration:none;" href="http://www.cppblog.com/herb/" target="_blank">herb</a> 2010-11-24 13:50 <a href="http://www.cppblog.com/herb/archive/2010/11/24/134502.html#Feedback" target="_blank" style="text-decoration:none;">发表评论</a></div>]]></description></item></channel></rss>