summaryrefslogtreecommitdiff
path: root/site/docs/1.5.0/storage-openstack-swift.html
diff options
context:
space:
mode:
authorReynold Xin <rxin@apache.org>2015-09-17 22:07:42 +0000
committerReynold Xin <rxin@apache.org>2015-09-17 22:07:42 +0000
commitee9ffe89d608e7640a2487406b618d27e58026d6 (patch)
tree50ec819abb41a9a769d7f64eed1f0ab2084aa6ff /site/docs/1.5.0/storage-openstack-swift.html
parentc7104724b279f09486ea62f4a24252e8d06f5c96 (diff)
downloadspark-website-ee9ffe89d608e7640a2487406b618d27e58026d6.tar.gz
spark-website-ee9ffe89d608e7640a2487406b618d27e58026d6.tar.bz2
spark-website-ee9ffe89d608e7640a2487406b618d27e58026d6.zip
delete 1.5.0
Diffstat (limited to 'site/docs/1.5.0/storage-openstack-swift.html')
-rw-r--r--site/docs/1.5.0/storage-openstack-swift.html307
1 files changed, 0 insertions, 307 deletions
diff --git a/site/docs/1.5.0/storage-openstack-swift.html b/site/docs/1.5.0/storage-openstack-swift.html
deleted file mode 100644
index 3525be4ee..000000000
--- a/site/docs/1.5.0/storage-openstack-swift.html
+++ /dev/null
@@ -1,307 +0,0 @@
-<!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>Accessing OpenStack Swift from Spark - 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">Accessing OpenStack Swift from Spark</h1>
-
-
- <p>Spark&#8217;s support for Hadoop InputFormat allows it to process data in OpenStack Swift using the
-same URI formats as in Hadoop. You can specify a path in Swift as input through a
-URI of the form <code>swift://container.PROVIDER/path</code>. You will also need to set your
-Swift security credentials, through <code>core-site.xml</code> or via
-<code>SparkContext.hadoopConfiguration</code>.
-Current Swift driver requires Swift to use Keystone authentication method.</p>
-
-<h1 id="configuring-swift-for-better-data-locality">Configuring Swift for Better Data Locality</h1>
-
-<p>Although not mandatory, it is recommended to configure the proxy server of Swift with
-<code>list_endpoints</code> to have better data locality. More information is
-<a href="https://github.com/openstack/swift/blob/master/swift/common/middleware/list_endpoints.py">available here</a>.</p>
-
-<h1 id="dependencies">Dependencies</h1>
-
-<p>The Spark application should include <code>hadoop-openstack</code> dependency.
-For example, for Maven support, add the following to the <code>pom.xml</code> file:</p>
-
-<div class="highlight"><pre><code class="language-xml" data-lang="xml"><span class="nt">&lt;dependencyManagement&gt;</span>
- ...
- <span class="nt">&lt;dependency&gt;</span>
- <span class="nt">&lt;groupId&gt;</span>org.apache.hadoop<span class="nt">&lt;/groupId&gt;</span>
- <span class="nt">&lt;artifactId&gt;</span>hadoop-openstack<span class="nt">&lt;/artifactId&gt;</span>
- <span class="nt">&lt;version&gt;</span>2.3.0<span class="nt">&lt;/version&gt;</span>
- <span class="nt">&lt;/dependency&gt;</span>
- ...
-<span class="nt">&lt;/dependencyManagement&gt;</span></code></pre></div>
-
-<h1 id="configuration-parameters">Configuration Parameters</h1>
-
-<p>Create <code>core-site.xml</code> and place it inside Spark&#8217;s <code>conf</code> directory.
-There are two main categories of parameters that should to be configured: declaration of the
-Swift driver and the parameters that are required by Keystone. </p>
-
-<p>Configuration of Hadoop to use Swift File system achieved via </p>
-
-<table class="table">
-<tr><th>Property Name</th><th>Value</th></tr>
-<tr>
- <td>fs.swift.impl</td>
- <td>org.apache.hadoop.fs.swift.snative.SwiftNativeFileSystem</td>
-</tr>
-</table>
-
-<p>Additional parameters required by Keystone (v2.0) and should be provided to the Swift driver. Those
-parameters will be used to perform authentication in Keystone to access Swift. The following table
-contains a list of Keystone mandatory parameters. <code>PROVIDER</code> can be any name.</p>
-
-<table class="table">
-<tr><th>Property Name</th><th>Meaning</th><th>Required</th></tr>
-<tr>
- <td><code>fs.swift.service.PROVIDER.auth.url</code></td>
- <td>Keystone Authentication URL</td>
- <td>Mandatory</td>
-</tr>
-<tr>
- <td><code>fs.swift.service.PROVIDER.auth.endpoint.prefix</code></td>
- <td>Keystone endpoints prefix</td>
- <td>Optional</td>
-</tr>
-<tr>
- <td><code>fs.swift.service.PROVIDER.tenant</code></td>
- <td>Tenant</td>
- <td>Mandatory</td>
-</tr>
-<tr>
- <td><code>fs.swift.service.PROVIDER.username</code></td>
- <td>Username</td>
- <td>Mandatory</td>
-</tr>
-<tr>
- <td><code>fs.swift.service.PROVIDER.password</code></td>
- <td>Password</td>
- <td>Mandatory</td>
-</tr>
-<tr>
- <td><code>fs.swift.service.PROVIDER.http.port</code></td>
- <td>HTTP port</td>
- <td>Mandatory</td>
-</tr>
-<tr>
- <td><code>fs.swift.service.PROVIDER.region</code></td>
- <td>Keystone region</td>
- <td>Mandatory</td>
-</tr>
-<tr>
- <td><code>fs.swift.service.PROVIDER.public</code></td>
- <td>Indicates if all URLs are public</td>
- <td>Mandatory</td>
-</tr>
-</table>
-
-<p>For example, assume <code>PROVIDER=SparkTest</code> and Keystone contains user <code>tester</code> with password <code>testing</code>
-defined for tenant <code>test</code>. Then <code>core-site.xml</code> should include:</p>
-
-<div class="highlight"><pre><code class="language-xml" data-lang="xml"><span class="nt">&lt;configuration&gt;</span>
- <span class="nt">&lt;property&gt;</span>
- <span class="nt">&lt;name&gt;</span>fs.swift.impl<span class="nt">&lt;/name&gt;</span>
- <span class="nt">&lt;value&gt;</span>org.apache.hadoop.fs.swift.snative.SwiftNativeFileSystem<span class="nt">&lt;/value&gt;</span>
- <span class="nt">&lt;/property&gt;</span>
- <span class="nt">&lt;property&gt;</span>
- <span class="nt">&lt;name&gt;</span>fs.swift.service.SparkTest.auth.url<span class="nt">&lt;/name&gt;</span>
- <span class="nt">&lt;value&gt;</span>http://127.0.0.1:5000/v2.0/tokens<span class="nt">&lt;/value&gt;</span>
- <span class="nt">&lt;/property&gt;</span>
- <span class="nt">&lt;property&gt;</span>
- <span class="nt">&lt;name&gt;</span>fs.swift.service.SparkTest.auth.endpoint.prefix<span class="nt">&lt;/name&gt;</span>
- <span class="nt">&lt;value&gt;</span>endpoints<span class="nt">&lt;/value&gt;</span>
- <span class="nt">&lt;/property&gt;</span>
- <span class="nt">&lt;name&gt;</span>fs.swift.service.SparkTest.http.port<span class="nt">&lt;/name&gt;</span>
- <span class="nt">&lt;value&gt;</span>8080<span class="nt">&lt;/value&gt;</span>
- <span class="nt">&lt;/property&gt;</span>
- <span class="nt">&lt;property&gt;</span>
- <span class="nt">&lt;name&gt;</span>fs.swift.service.SparkTest.region<span class="nt">&lt;/name&gt;</span>
- <span class="nt">&lt;value&gt;</span>RegionOne<span class="nt">&lt;/value&gt;</span>
- <span class="nt">&lt;/property&gt;</span>
- <span class="nt">&lt;property&gt;</span>
- <span class="nt">&lt;name&gt;</span>fs.swift.service.SparkTest.public<span class="nt">&lt;/name&gt;</span>
- <span class="nt">&lt;value&gt;</span>true<span class="nt">&lt;/value&gt;</span>
- <span class="nt">&lt;/property&gt;</span>
- <span class="nt">&lt;property&gt;</span>
- <span class="nt">&lt;name&gt;</span>fs.swift.service.SparkTest.tenant<span class="nt">&lt;/name&gt;</span>
- <span class="nt">&lt;value&gt;</span>test<span class="nt">&lt;/value&gt;</span>
- <span class="nt">&lt;/property&gt;</span>
- <span class="nt">&lt;property&gt;</span>
- <span class="nt">&lt;name&gt;</span>fs.swift.service.SparkTest.username<span class="nt">&lt;/name&gt;</span>
- <span class="nt">&lt;value&gt;</span>tester<span class="nt">&lt;/value&gt;</span>
- <span class="nt">&lt;/property&gt;</span>
- <span class="nt">&lt;property&gt;</span>
- <span class="nt">&lt;name&gt;</span>fs.swift.service.SparkTest.password<span class="nt">&lt;/name&gt;</span>
- <span class="nt">&lt;value&gt;</span>testing<span class="nt">&lt;/value&gt;</span>
- <span class="nt">&lt;/property&gt;</span>
-<span class="nt">&lt;/configuration&gt;</span></code></pre></div>
-
-<p>Notice that
-<code>fs.swift.service.PROVIDER.tenant</code>,
-<code>fs.swift.service.PROVIDER.username</code>,
-<code>fs.swift.service.PROVIDER.password</code> contains sensitive information and keeping them in
-<code>core-site.xml</code> is not always a good approach.
-We suggest to keep those parameters in <code>core-site.xml</code> for testing purposes when running Spark
-via <code>spark-shell</code>.
-For job submissions they should be provided via <code>sparkContext.hadoopConfiguration</code>.</p>
-
-
- </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>