summaryrefslogtreecommitdiff
path: root/site/docs/1.5.0/hadoop-provided.html
diff options
context:
space:
mode:
authorReynold Xin <rxin@apache.org>2015-09-17 22:11:21 +0000
committerReynold Xin <rxin@apache.org>2015-09-17 22:11:21 +0000
commit6f57b0c45a7d1b6255067c6e9bc549baa491acac (patch)
treedbf7d7a7700e9e6bad3c8289ab831bc9c2c20d62 /site/docs/1.5.0/hadoop-provided.html
parentee9ffe89d608e7640a2487406b618d27e58026d6 (diff)
downloadspark-website-6f57b0c45a7d1b6255067c6e9bc549baa491acac.tar.gz
spark-website-6f57b0c45a7d1b6255067c6e9bc549baa491acac.tar.bz2
spark-website-6f57b0c45a7d1b6255067c6e9bc549baa491acac.zip
add 1.5.0 back
Diffstat (limited to 'site/docs/1.5.0/hadoop-provided.html')
-rw-r--r--site/docs/1.5.0/hadoop-provided.html184
1 files changed, 184 insertions, 0 deletions
diff --git a/site/docs/1.5.0/hadoop-provided.html b/site/docs/1.5.0/hadoop-provided.html
new file mode 100644
index 000000000..ebe0a4b79
--- /dev/null
+++ b/site/docs/1.5.0/hadoop-provided.html
@@ -0,0 +1,184 @@
+<!DOCTYPE html>
+<!--[if lt IE 7]> <html class="no-js lt-ie9 lt-ie8 lt-ie7"> <![endif]-->
+<!--[if IE 7]> <html class="no-js lt-ie9 lt-ie8"> <![endif]-->
+<!--[if IE 8]> <html class="no-js lt-ie9"> <![endif]-->
+<!--[if gt IE 8]><!--> <html class="no-js"> <!--<![endif]-->
+ <head>
+ <meta charset="utf-8">
+ <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">
+ <title>Using Spark's "Hadoop Free" Build - Spark 1.5.0 Documentation</title>
+
+
+
+
+ <link rel="stylesheet" href="css/bootstrap.min.css">
+ <style>
+ body {
+ padding-top: 60px;
+ padding-bottom: 40px;
+ }
+ </style>
+ <meta name="viewport" content="width=device-width">
+ <link rel="stylesheet" href="css/bootstrap-responsive.min.css">
+ <link rel="stylesheet" href="css/main.css">
+
+ <script src="js/vendor/modernizr-2.6.1-respond-1.1.0.min.js"></script>
+
+ <link rel="stylesheet" href="css/pygments-default.css">
+
+
+ <!-- Google analytics script -->
+ <script type="text/javascript">
+ var _gaq = _gaq || [];
+ _gaq.push(['_setAccount', 'UA-32518208-2']);
+ _gaq.push(['_trackPageview']);
+
+ (function() {
+ var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
+ ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
+ var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
+ })();
+ </script>
+
+
+ </head>
+ <body>
+ <!--[if lt IE 7]>
+ <p class="chromeframe">You are using an outdated browser. <a href="http://browsehappy.com/">Upgrade your browser today</a> or <a href="http://www.google.com/chromeframe/?redirect=true">install Google Chrome Frame</a> to better experience this site.</p>
+ <![endif]-->
+
+ <!-- This code is taken from http://twitter.github.com/bootstrap/examples/hero.html -->
+
+ <div class="navbar navbar-fixed-top" id="topbar">
+ <div class="navbar-inner">
+ <div class="container">
+ <div class="brand"><a href="index.html">
+ <img src="img/spark-logo-hd.png" style="height:50px;"/></a><span class="version">1.5.0</span>
+ </div>
+ <ul class="nav">
+ <!--TODO(andyk): Add class="active" attribute to li some how.-->
+ <li><a href="index.html">Overview</a></li>
+
+ <li class="dropdown">
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">Programming Guides<b class="caret"></b></a>
+ <ul class="dropdown-menu">
+ <li><a href="quick-start.html">Quick Start</a></li>
+ <li><a href="programming-guide.html">Spark Programming Guide</a></li>
+ <li class="divider"></li>
+ <li><a href="streaming-programming-guide.html">Spark Streaming</a></li>
+ <li><a href="sql-programming-guide.html">DataFrames and SQL</a></li>
+ <li><a href="mllib-guide.html">MLlib (Machine Learning)</a></li>
+ <li><a href="graphx-programming-guide.html">GraphX (Graph Processing)</a></li>
+ <li><a href="bagel-programming-guide.html">Bagel (Pregel on Spark)</a></li>
+ <li><a href="sparkr.html">SparkR (R on Spark)</a></li>
+ </ul>
+ </li>
+
+ <li class="dropdown">
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">API Docs<b class="caret"></b></a>
+ <ul class="dropdown-menu">
+ <li><a href="api/scala/index.html#org.apache.spark.package">Scala</a></li>
+ <li><a href="api/java/index.html">Java</a></li>
+ <li><a href="api/python/index.html">Python</a></li>
+ <li><a href="api/R/index.html">R</a></li>
+ </ul>
+ </li>
+
+ <li class="dropdown">
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">Deploying<b class="caret"></b></a>
+ <ul class="dropdown-menu">
+ <li><a href="cluster-overview.html">Overview</a></li>
+ <li><a href="submitting-applications.html">Submitting Applications</a></li>
+ <li class="divider"></li>
+ <li><a href="spark-standalone.html">Spark Standalone</a></li>
+ <li><a href="running-on-mesos.html">Mesos</a></li>
+ <li><a href="running-on-yarn.html">YARN</a></li>
+ <li class="divider"></li>
+ <li><a href="ec2-scripts.html">Amazon EC2</a></li>
+ </ul>
+ </li>
+
+ <li class="dropdown">
+ <a href="api.html" class="dropdown-toggle" data-toggle="dropdown">More<b class="caret"></b></a>
+ <ul class="dropdown-menu">
+ <li><a href="configuration.html">Configuration</a></li>
+ <li><a href="monitoring.html">Monitoring</a></li>
+ <li><a href="tuning.html">Tuning Guide</a></li>
+ <li><a href="job-scheduling.html">Job Scheduling</a></li>
+ <li><a href="security.html">Security</a></li>
+ <li><a href="hardware-provisioning.html">Hardware Provisioning</a></li>
+ <li><a href="hadoop-third-party-distributions.html">3<sup>rd</sup>-Party Hadoop Distros</a></li>
+ <li class="divider"></li>
+ <li><a href="building-spark.html">Building Spark</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark">Contributing to Spark</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Supplemental+Spark+Projects">Supplemental Projects</a></li>
+ </ul>
+ </li>
+ </ul>
+ <!--<p class="navbar-text pull-right"><span class="version-text">v1.5.0</span></p>-->
+ </div>
+ </div>
+ </div>
+
+ <div class="container" id="content">
+
+ <h1 class="title">Using Spark's "Hadoop Free" Build</h1>
+
+
+ <p>Spark uses Hadoop client libraries for HDFS and YARN. Starting in version Spark 1.4, the project packages &#8220;Hadoop free&#8221; builds that lets you more easily connect a single Spark binary to any Hadoop version. To use these builds, you need to modify <code>SPARK_DIST_CLASSPATH</code> to include Hadoop&#8217;s package jars. The most convenient place to do this is by adding an entry in <code>conf/spark-env.sh</code>.</p>
+
+<p>This page describes how to connect Spark to Hadoop for different types of distributions.</p>
+
+<h1 id="apache-hadoop">Apache Hadoop</h1>
+<p>For Apache distributions, you can use Hadoop&#8217;s &#8216;classpath&#8217; command. For instance:</p>
+
+<div class="highlight"><pre><code class="language-bash" data-lang="bash"><span class="c">### in conf/spark-env.sh ###</span>
+
+<span class="c"># If &#39;hadoop&#39; binary is on your PATH</span>
+<span class="nb">export </span><span class="nv">SPARK_DIST_CLASSPATH</span><span class="o">=</span><span class="k">$(</span>hadoop classpath<span class="k">)</span>
+
+<span class="c"># With explicit path to &#39;hadoop&#39; binary</span>
+<span class="nb">export </span><span class="nv">SPARK_DIST_CLASSPATH</span><span class="o">=</span><span class="k">$(</span>/path/to/hadoop/bin/hadoop classpath<span class="k">)</span>
+
+<span class="c"># Passing a Hadoop configuration directory</span>
+<span class="nb">export </span><span class="nv">SPARK_DIST_CLASSPATH</span><span class="o">=</span><span class="k">$(</span>hadoop --config /path/to/configs classpath<span class="k">)</span></code></pre></div>
+
+
+
+ </div> <!-- /container -->
+
+ <script src="js/vendor/jquery-1.8.0.min.js"></script>
+ <script src="js/vendor/bootstrap.min.js"></script>
+ <script src="js/vendor/anchor.min.js"></script>
+ <script src="js/main.js"></script>
+
+ <!-- MathJax Section -->
+ <script type="text/x-mathjax-config">
+ MathJax.Hub.Config({
+ TeX: { equationNumbers: { autoNumber: "AMS" } }
+ });
+ </script>
+ <script>
+ // Note that we load MathJax this way to work with local file (file://), HTTP and HTTPS.
+ // We could use "//cdn.mathjax...", but that won't support "file://".
+ (function(d, script) {
+ script = d.createElement('script');
+ script.type = 'text/javascript';
+ script.async = true;
+ script.onload = function(){
+ MathJax.Hub.Config({
+ tex2jax: {
+ inlineMath: [ ["$", "$"], ["\\\\(","\\\\)"] ],
+ displayMath: [ ["$$","$$"], ["\\[", "\\]"] ],
+ processEscapes: true,
+ skipTags: ['script', 'noscript', 'style', 'textarea', 'pre']
+ }
+ });
+ };
+ script.src = ('https:' == document.location.protocol ? 'https://' : 'http://') +
+ 'cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML';
+ d.getElementsByTagName('head')[0].appendChild(script);
+ }(document));
+ </script>
+ </body>
+</html>