123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462 |
- <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
- <html>
- <head>
- <META http-equiv="Content-Type" content="text/html; charset=UTF-8">
- <meta content="Apache Forrest" name="Generator">
- <meta name="Forrest-version" content="0.8">
- <meta name="Forrest-skin-name" content="pelt">
- <title>Hadoop本地库</title>
- <link type="text/css" href="skin/basic.css" rel="stylesheet">
- <link media="screen" type="text/css" href="skin/screen.css" rel="stylesheet">
- <link media="print" type="text/css" href="skin/print.css" rel="stylesheet">
- <link type="text/css" href="skin/profile.css" rel="stylesheet">
- <script src="skin/getBlank.js" language="javascript" type="text/javascript"></script><script src="skin/getMenu.js" language="javascript" type="text/javascript"></script><script src="skin/fontsize.js" language="javascript" type="text/javascript"></script>
- <link rel="shortcut icon" href="images/favicon.ico">
- </head>
- <body onload="init()">
- <script type="text/javascript">ndeSetTextSize();</script>
- <div id="top">
- <!--+
- |breadtrail
- +-->
- <div class="breadtrail">
- <a href="http://www.apache.org/">Apache</a> > <a href="http://hadoop.apache.org/">Hadoop</a> > <a href="http://hadoop.apache.org/core/">Core</a><script src="skin/breadcrumbs.js" language="JavaScript" type="text/javascript"></script>
- </div>
- <!--+
- |header
- +-->
- <div class="header">
- <!--+
- |start group logo
- +-->
- <div class="grouplogo">
- <a href="http://hadoop.apache.org/"><img class="logoImage" alt="Hadoop" src="images/hadoop-logo.jpg" title="Apache Hadoop"></a>
- </div>
- <!--+
- |end group logo
- +-->
- <!--+
- |start Project Logo
- +-->
- <div class="projectlogo">
- <a href="http://hadoop.apache.org/core/"><img class="logoImage" alt="Hadoop" src="images/core-logo.gif" title="Scalable Computing Platform"></a>
- </div>
- <!--+
- |end Project Logo
- +-->
- <!--+
- |start Search
- +-->
- <div class="searchbox">
- <form action="http://www.google.com/search" method="get" class="roundtopsmall">
- <input value="hadoop.apache.org" name="sitesearch" type="hidden"><input onFocus="getBlank (this, 'Search the site with google');" size="25" name="q" id="query" type="text" value="Search the site with google">
- <input name="Search" value="Search" type="submit">
- </form>
- </div>
- <!--+
- |end search
- +-->
- <!--+
- |start Tabs
- +-->
- <ul id="tabs">
- <li>
- <a class="unselected" href="http://hadoop.apache.org/core/">项目</a>
- </li>
- <li>
- <a class="unselected" href="http://wiki.apache.org/hadoop">维基</a>
- </li>
- <li class="current">
- <a class="selected" href="index.html">Hadoop 0.18文档</a>
- </li>
- </ul>
- <!--+
- |end Tabs
- +-->
- </div>
- </div>
- <div id="main">
- <div id="publishedStrip">
- <!--+
- |start Subtabs
- +-->
- <div id="level2tabs"></div>
- <!--+
- |end Endtabs
- +-->
- <script type="text/javascript"><!--
- document.write("Last Published: " + document.lastModified);
- // --></script>
- </div>
- <!--+
- |breadtrail
- +-->
- <div class="breadtrail">
-
- </div>
- <!--+
- |start Menu, mainarea
- +-->
- <!--+
- |start Menu
- +-->
- <div id="menu">
- <div onclick="SwitchMenu('menu_selected_1.1', 'skin/')" id="menu_selected_1.1Title" class="menutitle" style="background-image: url('skin/images/chapter_open.gif');">文档</div>
- <div id="menu_selected_1.1" class="selectedmenuitemgroup" style="display: block;">
- <div class="menuitem">
- <a href="index.html">概述</a>
- </div>
- <div class="menuitem">
- <a href="quickstart.html">快速入门</a>
- </div>
- <div class="menuitem">
- <a href="cluster_setup.html">集群搭建</a>
- </div>
- <div class="menuitem">
- <a href="hdfs_design.html">HDFS构架设计</a>
- </div>
- <div class="menuitem">
- <a href="hdfs_user_guide.html">HDFS使用指南</a>
- </div>
- <div class="menuitem">
- <a href="hdfs_permissions_guide.html">HDFS权限指南</a>
- </div>
- <div class="menuitem">
- <a href="hdfs_quota_admin_guide.html">HDFS配额管理指南</a>
- </div>
- <div class="menuitem">
- <a href="commands_manual.html">命令手册</a>
- </div>
- <div class="menuitem">
- <a href="hdfs_shell.html">FS Shell使用指南</a>
- </div>
- <div class="menuitem">
- <a href="distcp.html">DistCp使用指南</a>
- </div>
- <div class="menuitem">
- <a href="mapred_tutorial.html">Map-Reduce教程</a>
- </div>
- <div class="menupage">
- <div class="menupagetitle">Hadoop本地库</div>
- </div>
- <div class="menuitem">
- <a href="streaming.html">Streaming</a>
- </div>
- <div class="menuitem">
- <a href="hadoop_archives.html">Hadoop Archives</a>
- </div>
- <div class="menuitem">
- <a href="hod.html">Hadoop On Demand</a>
- </div>
- <div class="menuitem">
- <a href="http://hadoop.apache.org/core/docs/r0.18.2/api/index.html">API参考</a>
- </div>
- <div class="menuitem">
- <a href="http://hadoop.apache.org/core/docs/r0.18.2/jdiff/changes.html">API Changes</a>
- </div>
- <div class="menuitem">
- <a href="http://wiki.apache.org/hadoop/">维基</a>
- </div>
- <div class="menuitem">
- <a href="http://wiki.apache.org/hadoop/FAQ">常见问题</a>
- </div>
- <div class="menuitem">
- <a href="http://hadoop.apache.org/core/mailing_lists.html">邮件列表</a>
- </div>
- <div class="menuitem">
- <a href="http://hadoop.apache.org/core/docs/r0.18.2/releasenotes.html">发行说明</a>
- </div>
- <div class="menuitem">
- <a href="http://hadoop.apache.org/core/docs/r0.18.2/changes.html">变更日志</a>
- </div>
- </div>
- <div id="credit"></div>
- <div id="roundbottom">
- <img style="display: none" class="corner" height="15" width="15" alt="" src="skin/images/rc-b-l-15-1body-2menu-3menu.png"></div>
- <!--+
- |alternative credits
- +-->
- <div id="credit2"></div>
- </div>
- <!--+
- |end Menu
- +-->
- <!--+
- |start content
- +-->
- <div id="content">
- <div title="Portable Document Format" class="pdflink">
- <a class="dida" href="native_libraries.pdf"><img alt="PDF -icon" src="skin/images/pdfdoc.gif" class="skin"><br>
- PDF</a>
- </div>
- <h1>Hadoop本地库</h1>
- <div id="minitoc-area">
- <ul class="minitoc">
- <li>
- <a href="#%E7%9B%AE%E7%9A%84">目的</a>
- </li>
- <li>
- <a href="#%E7%BB%84%E4%BB%B6">组件</a>
- </li>
- <li>
- <a href="#%E4%BD%BF%E7%94%A8%E6%96%B9%E6%B3%95">使用方法</a>
- </li>
- <li>
- <a href="#%E6%94%AF%E6%8C%81%E7%9A%84%E5%B9%B3%E5%8F%B0">支持的平台</a>
- </li>
- <li>
- <a href="#%E6%9E%84%E5%BB%BAHadoop%E6%9C%AC%E5%9C%B0%E5%BA%93">构建Hadoop本地库</a>
- <ul class="minitoc">
- <li>
- <a href="#%E6%B3%A8%E6%84%8F">注意</a>
- </li>
- </ul>
- </li>
- <li>
- <a href="#%E4%BD%BF%E7%94%A8DistributedCache+%E5%8A%A0%E8%BD%BD%E6%9C%AC%E5%9C%B0%E5%BA%93"> 使用DistributedCache 加载本地库</a>
- </li>
- </ul>
- </div>
-
-
- <a name="N1000D"></a><a name="%E7%9B%AE%E7%9A%84"></a>
- <h2 class="h3">目的</h2>
- <div class="section">
- <p>
- 鉴于性能问题以及某些Java类库的缺失,对于某些组件,Hadoop提供了自己的本地实现。
- 这些组件保存在Hadoop的一个独立的动态链接的库里。这个库在*nix平台上叫<em>libhadoop.so</em>. 本文主要介绍本地库的使用方法以及如何构建本地库。
- </p>
- </div>
-
-
- <a name="N1001A"></a><a name="%E7%BB%84%E4%BB%B6"></a>
- <h2 class="h3">组件</h2>
- <div class="section">
- <p>Hadoop现在已经有以下
- <a href="http://hadoop.apache.org/core/docs/r0.18.2/api/org/apache/hadoop/io/compress/CompressionCodec.html">
- compression codecs</a>本地组件:</p>
- <ul>
-
- <li>
- <a href="http://www.zlib.net/">zlib</a>
- </li>
-
- <li>
- <a href="http://www.gzip.org/">gzip</a>
- </li>
-
- <li>
- <a href="http://www.oberhumer.com/opensource/lzo/">lzo</a>
- </li>
-
- </ul>
- <p>在以上组件中,lzo和gzip压缩编解码器必须使用hadoop本地库才能运行。
- </p>
- </div>
-
- <a name="N1003D"></a><a name="%E4%BD%BF%E7%94%A8%E6%96%B9%E6%B3%95"></a>
- <h2 class="h3">使用方法</h2>
- <div class="section">
- <p>hadoop本地库的用法很简单:</p>
- <ul>
-
- <li>
- 看一下
- <a href="#%E6%94%AF%E6%8C%81%E7%9A%84%E5%B9%B3%E5%8F%B0">支持的平台</a>.
- </li>
-
- <li>
-
- <a href="http://hadoop.apache.org/core/releases.html#Download">下载</a> 预构建的32位i386架构的Linux本地hadoop库(可以在hadoop发行版的<span class="codefrag">lib/native</span>目录下找到)或者自己
- <a href="#%E6%9E%84%E5%BB%BAHadoop%E6%9C%AC%E5%9C%B0%E5%BA%93">构建</a> 这些库。
- </li>
-
- <li>
- 确保你的平台已经安装了<strong>zlib-1.2</strong>以上版本或者<strong>lzo2.0</strong>以上版本的软件包或者两者均已安装(根据你的需要)。
- </li>
-
- </ul>
- <p>
- <span class="codefrag">bin/hadoop</span> 脚本通过系统属性
- <em>-Djava.library.path=<path></em>来确认hadoop本地库是否包含在库路径里。</p>
- <p>检查hadoop日志文件可以查看hadoop库是否正常,正常情况下会看到:</p>
- <p>
-
- <span class="codefrag">
- DEBUG util.NativeCodeLoader - Trying to load the custom-built
- native-hadoop library...
- </span>
- <br>
-
- <span class="codefrag">
- INFO util.NativeCodeLoader - Loaded the native-hadoop library
- </span>
-
- </p>
- <p>如果出错,会看到:</p>
- <p>
-
- <span class="codefrag">
- INFO util.NativeCodeLoader - Unable to load native-hadoop library for
- your platform... using builtin-java classes where applicable
- </span>
-
- </p>
- </div>
-
-
- <a name="N10086"></a><a name="%E6%94%AF%E6%8C%81%E7%9A%84%E5%B9%B3%E5%8F%B0"></a>
- <h2 class="h3">支持的平台</h2>
- <div class="section">
- <p>Hadoop本地库只支持*nix平台,已经广泛使用在GNU/Linux平台上,但是不支持
- <a href="http://www.cygwin.com/">Cygwin</a>
- 和 <a href="http://www.apple.com/macosx">Mac OS X</a>。
- </p>
- <p>已经测试过的GNU/Linux发行版本:</p>
- <ul>
-
- <li>
-
- <a href="http://www.redhat.com/rhel/">RHEL4</a>/<a href="http://fedora.redhat.com/">Fedora</a>
-
- </li>
-
- <li>
- <a href="http://www.ubuntu.com/">Ubuntu</a>
- </li>
-
- <li>
- <a href="http://www.gentoo.org/">Gentoo</a>
- </li>
-
- </ul>
- <p>在上述平台上,32/64位Hadoop本地库分别能和32/64位的jvm一起正常运行。
- </p>
- </div>
-
-
- <a name="N100B6"></a><a name="%E6%9E%84%E5%BB%BAHadoop%E6%9C%AC%E5%9C%B0%E5%BA%93"></a>
- <h2 class="h3">构建Hadoop本地库</h2>
- <div class="section">
- <p>Hadoop本地库使用
- <a href="http://en.wikipedia.org/wiki/ANSI_C">ANSI C</a> 编写,使用GNU autotools工具链 (autoconf, autoheader, automake, autoscan, libtool)构建。也就是说构建hadoop库的平台需要有标准C的编译器和GNU autotools工具链。请参看
- <a href="#%E6%94%AF%E6%8C%81%E7%9A%84%E5%B9%B3%E5%8F%B0">支持的平台</a>。</p>
- <p>你的目标平台上可能会需要的软件包:
- </p>
- <ul>
-
- <li>
- C 编译器 (e.g. <a href="http://gcc.gnu.org/">GNU C Compiler</a>)
- </li>
-
- <li>
- GNU Autools 工具链:
- <a href="http://www.gnu.org/software/autoconf/">autoconf</a>,
- <a href="http://www.gnu.org/software/automake/">automake</a>,
- <a href="http://www.gnu.org/software/libtool/">libtool</a>
-
- </li>
-
- <li>
- zlib开发包 (stable version >= 1.2.0)
- </li>
-
- <li>
- lzo开发包 (stable version >= 2.0)
- </li>
-
- </ul>
- <p>如果已经满足了上述先决条件,可以使用<span class="codefrag">build.xml</span>
- 文件,并把其中的<span class="codefrag">compile.native</span>置为
- <span class="codefrag">true</span>,这样就可以生成hadoop本地库:</p>
- <p>
- <span class="codefrag">$ ant -Dcompile.native=true <target></span>
- </p>
- <p>因为不是所有用户都需要Hadoop本地库,所以默认情况下hadoop不生成该库。
- </p>
- <p>你可以在下面的路径查看新生成的hadoop本地库:</p>
- <p>
- <span class="codefrag">$ build/native/<platform>/lib</span>
- </p>
- <p>其中<platform>是下列系统属性的组合
- <span class="codefrag">${os.name}-${os.arch}-${sun.arch.data.model}</span>;例如
- Linux-i386-32。</p>
- <a name="N10109"></a><a name="%E6%B3%A8%E6%84%8F"></a>
- <h3 class="h4">注意</h3>
- <ul>
-
- <li>
- 在生成hadoop本地库的目标平台上<strong>必须</strong> 安装了zlib和lzo开发包;但是如果你只希望使用其中一个的话,在部署时,安装其中任何一个都是足够的。
- </li>
-
- <li>
- 在目标平台上生成以及部署hadoop本地库时,都需要根据32/64位jvm选取对应的32/64位zlib/lzo软件包。
- </li>
-
- </ul>
- </div>
- <!--DCCOMMENT:diff begin-->
-
- <a name="N1011F"></a><a name="%E4%BD%BF%E7%94%A8DistributedCache+%E5%8A%A0%E8%BD%BD%E6%9C%AC%E5%9C%B0%E5%BA%93"></a>
- <h2 class="h3"> 使用DistributedCache 加载本地库</h2>
- <div class="section">
- <p>用户可以通过
- <a href="mapred_tutorial.html#DistributedCache">DistributedCache</a>
- 加载本地共享库,并<em>分发</em>和建立库文件的<em>符号链接</em>。
- </p>
- <p>这个例子描述了如何分发库文件并在从map/reduce任务中装载库文件。
- </p>
- <ol>
-
- <li>首先拷贝库文件到HDFS。<br>
-
- <span class="codefrag">bin/hadoop fs -copyFromLocal mylib.so.1 /libraries/mylib.so.1</span>
-
- </li>
-
- <li>启动作业时包含以下代码:<br>
-
- <span class="codefrag"> DistributedCache.createSymlink(conf); </span>
- <br>
-
- <span class="codefrag"> DistributedCache.addCacheFile("hdfs://host:port/libraries/mylib.so.1#mylib.so", conf);
- </span>
-
- </li>
-
- <li>map/reduce任务中包含以下代码:<br>
-
- <span class="codefrag"> System.loadLibrary("mylib.so"); </span>
-
- </li>
-
- </ol>
- </div>
-
- </div>
- <!--+
- |end content
- +-->
- <div class="clearboth"> </div>
- </div>
- <div id="footer">
- <!--+
- |start bottomstrip
- +-->
- <div class="lastmodified">
- <script type="text/javascript"><!--
- document.write("Last Published: " + document.lastModified);
- // --></script>
- </div>
- <div class="copyright">
- Copyright ©
- 2007 <a href="http://www.apache.org/licenses/">The Apache Software Foundation.</a>
- </div>
- <!--+
- |end bottomstrip
- +-->
- </div>
- </body>
- </html>
|