diff options
Diffstat (limited to 'site/documentation.html')
| -rw-r--r-- | site/documentation.html | 308 |
1 files changed, 175 insertions, 133 deletions
diff --git a/site/documentation.html b/site/documentation.html index 697919801..a2aae3e54 100644 --- a/site/documentation.html +++ b/site/documentation.html @@ -1,27 +1,20 @@ <!DOCTYPE html> -<!--[if IE 6]> -<html id="ie6" dir="ltr" lang="en-US"> -<![endif]--> -<!--[if IE 7]> -<html id="ie7" dir="ltr" lang="en-US"> -<![endif]--> -<!--[if IE 8]> -<html id="ie8" dir="ltr" lang="en-US"> -<![endif]--> -<!--[if !(IE 6) | !(IE 7) | !(IE 8) ]><!--> -<html dir="ltr" lang="en-US"> -<!--<![endif]--> +<html lang="en"> <head> - <link rel="shortcut icon" href="/favicon.ico" /> - <meta charset="UTF-8" /> - <meta name="viewport" content="width=device-width" /> + <meta charset="utf-8"> + <meta http-equiv="X-UA-Compatible" content="IE=edge"> + <meta name="viewport" content="width=device-width, initial-scale=1.0"> + <title> Documentation | Apache Spark </title> - <link rel="stylesheet" type="text/css" media="all" href="/css/style.css" /> - <link rel="stylesheet" href="/css/pygments-default.css"> + + + <!-- Bootstrap core CSS --> + <link href="/css/cerulean.min.css" rel="stylesheet"> + <link href="/css/custom.css" rel="stylesheet"> <script type="text/javascript"> <!-- Google Analytics initialization --> @@ -46,102 +39,137 @@ } </script> - <link rel='canonical' href='/index.html' /> - - <style type="text/css"> - #site-title, - #site-description { - position: absolute !important; - clip: rect(1px 1px 1px 1px); /* IE6, IE7 */ - clip: rect(1px, 1px, 1px, 1px); - } - </style> - <style type="text/css" id="custom-background-css"> - body.custom-background { background-color: #f1f1f1; } - </style> + <!-- HTML5 shim and Respond.js IE8 support of HTML5 elements and media queries --> + <!--[if lt IE 9]> + <script src="https://oss.maxcdn.com/libs/html5shiv/3.7.0/html5shiv.js"></script> + <script src="https://oss.maxcdn.com/libs/respond.js/1.3.0/respond.min.js"></script> + <![endif]--> </head> -<!--body class="page singular"--> -<body class="page singular"> -<div id="page" class="hfeed"> - - <header id="branding" role="banner"> - <hgroup> - <h1 id="site-title"><span><a href="/" title="Spark" rel="home">Spark</a></span></h1> - <h2 id="site-description">Lightning-Fast Cluster Computing</h2> - </hgroup> - - <a id="main-logo" href="/"> - <img style="height:175px; width:auto;" src="/images/spark-project-header1-cropped.png" alt="Spark: Lightning-Fast Cluster Computing" title="Spark: Lightning-Fast Cluster Computing" /> - </a> - <div class="widget-summit"> - <a href="http://spark-summit.org"><img src="/images/Summit-Logo-FINALtr-150x150px.png" /></a> - <div class="text"> - <a href="http://spark-summit.org/2013"> - - <strong>Videos and Slides<br/> - Available Now!</strong> - </a> - </div> +<body> + +<div class="container" style="max-width: 1200px;"> + +<div class="masthead"> + + <p class="lead"> + <a href="/"> + <img src="/images/spark-logo.png" + style="height:100px; width:auto; vertical-align: bottom; margin-top: 20px;"></a><span class="tagline"> + Lightning-fast cluster computing + </span> + </p> + +</div> + +<nav class="navbar navbar-default" role="navigation"> + <!-- Brand and toggle get grouped for better mobile display --> + <div class="navbar-header"> + <button type="button" class="navbar-toggle" data-toggle="collapse" + data-target="#navbar-collapse-1"> + <span class="sr-only">Toggle navigation</span> + <span class="icon-bar"></span> + <span class="icon-bar"></span> + <span class="icon-bar"></span> + </button> </div> - <nav id="access" role="navigation"> - <h3 class="assistive-text">Main menu</h3> - <div class="menu-main-menu-container"> - <ul id="menu-main-menu" class="menu"> - - <li class="menu-item menu-item-type-post_type menu-item-object-page "> - <a href="/index.html">Home</a> - </li> - - <li class="menu-item menu-item-type-post_type menu-item-object-page "> - <a href="/downloads.html">Downloads</a> - </li> - - <li class="menu-item menu-item-type-post_type menu-item-object-page current-menu-item"> - <a href="/documentation.html">Documentation</a> - </li> + <!-- Collect the nav links, forms, and other content for toggling --> + <div class="collapse navbar-collapse" id="navbar-collapse-1"> + <ul class="nav navbar-nav"> + <li><a href="/downloads.html">Download</a></li> + <li class="dropdown"> + <a href="#" class="dropdown-toggle" data-toggle="dropdown"> + Related Projects <b class="caret"></b> + </a> + <ul class="dropdown-menu"> + <li><a href="http://shark.cs.berkeley.edu">Shark (SQL)</a></li> + <li><a href="/streaming/">Spark Streaming</a></li> + <li><a href="/mllib/">MLlib (machine learning)</a></li> + <li><a href="http://amplab.github.io/graphx/">GraphX (graph)</a></li> + </ul> + </li> + <li class="dropdown"> + <a href="#" class="dropdown-toggle" data-toggle="dropdown"> + Documentation <b class="caret"></b> + </a> + <ul class="dropdown-menu"> + <li><a href="/documentation.html">Overview</a></li> + <li><a href="/docs/latest/">Latest Release</a></li> + <li><a href="/examples.html">Examples</a></li> + </ul> + </li> + <li class="dropdown"> + <a href="#" class="dropdown-toggle" data-toggle="dropdown"> + Community <b class="caret"></b> + </a> + <ul class="dropdown-menu"> + <li><a href="/community.html">Mailing Lists</a></li> + <li><a href="/community.html#events">Events and Meetups</a></li> + <li><a href="/community.html#history">Project History</a></li> + <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Powered+By+Spark">Powered By</a></li> + </ul> + </li> + <li><a href="/faq.html">FAQ</a></li> + </ul> + </div> + <!-- /.navbar-collapse --> +</nav> + + +<div class="row"> + <div class="col-md-3 col-md-push-9"> + <div class="news" style="margin-bottom: 20px;"> + <h5>Latest News</h5> + <ul class="list-unstyled"> - <li class="menu-item menu-item-type-post_type menu-item-object-page "> - <a href="/examples.html">Examples</a> - </li> + <li><a href="/news/spark-0-8-1-released.html">Spark 0.8.1 released</a> + <span class="small">(Dec 19, 2013)</span></li> - <li class="menu-item menu-item-type-post_type menu-item-object-page "> - <a href="/mailing-lists.html">Mailing Lists</a> - </li> + <li><a href="/news/spark-summit-2013-is-a-wrap.html">Spark Summit 2013 is a Wrap</a> + <span class="small">(Dec 15, 2013)</span></li> - <li class="menu-item menu-item-type-post_type menu-item-object-page "> - <a href="/research.html">Research</a> - </li> + <li><a href="/news/announcing-the-first-spark-summit.html">Announcing the first Spark Summit: December 2, 2013</a> + <span class="small">(Oct 08, 2013)</span></li> - <li class="menu-item menu-item-type-post_type menu-item-object-page "> - <a href="/faq.html">FAQ</a> - </li> + <li><a href="/news/spark-0-8-0-released.html">Spark 0.8.0 released</a> + <span class="small">(Sep 25, 2013)</span></li> - </ul></div> - </nav><!-- #access --> -</header><!-- #branding --> - - + </ul> + <p class="small" style="text-align: right;"><a href="/news/index.html">Archive</a></p> + </div> + <div class="hidden-xs hidden-sm"> + <a href="/downloads.html" class="btn btn-success btn-lg btn-block" style="margin-bottom: 30px;"> + Download Spark + </a> + <p style="font-size: 16px; font-weight: 500; color: #555;"> + Related Projects: + </p> + <ul class="list-narrow"> + <li><a href="http://shark.cs.berkeley.edu">Shark (SQL)</a></li> + <li><a href="/streaming/">Spark Streaming</a></li> + <li><a href="/mllib/">MLlib (machine learning)</a></li> + <li><a href="http://amplab.github.io/graphx/">GraphX (graph)</a></li> + </ul> + </div> + </div> - <div id="main"> - <div id="primary"> - <div id="content" role="main"> - - <article class="page type-page status-publish hentry"> - <h2>Spark Documentation</h2> + <div class="col-md-9 col-md-pull-3"> + <h2>Spark Documentation</h2> <p>Setup instructions, programming guides, and other documentation are available for each version of Spark below:</p> <ul> <li><a href="/docs/latest/">Spark 0.8.1 (latest release)</a></li> - <li><a href="/docs/0.8.0/">Spark 0.8.0</a></li> <li><a href="/docs/0.7.3/">Spark 0.7.3</a></li> <li><a href="/docs/0.6.2/">Spark 0.6.2</a></li> - <li><a href="https://github.com/mesos/spark/wiki/Spark-0.5-Documentation">Spark 0.5.x</a> (hosted on GitHub)</li> </ul> -<p>Read these documents to get started with Spark. In addition, this page lists some external resources for learning Spark.</p> +<p>Read these documents to get started with Spark, as well as with the built-in components +(<a href="/docs/latest/mllib-guide.html">MLlib</a> and +<a href="/docs/latest/streaming-programming-guide.html">Spark Streaming</a>).</p> + +<p>In addition, this page lists some external resources for learning Spark.</p> <h3>Video Tutorials</h3> @@ -156,23 +184,37 @@ <h3>Hands-On Exercises</h3> <ul> - <li><a href="http://ampcamp.berkeley.edu/3/exercises/">Hands-on exercises</a> are available online. These exercises let you launch a small EC2 cluster, load a dataset, and query it with Spark, Shark, Spark Streaming, and MLLib.</li> + <li><a href="http://spark-summit.org/2013/exercises/">Hands-on exercises</a> are available online from Spark Summit 2013. These exercises let you launch a small EC2 cluster, load a dataset, and query it with Spark, Shark, Spark Streaming, and MLLib.</li> </ul> -<h3>Spark Summit Slides and Videos</h3> +<p><a name="summit"></a></p> +<h3>Training Materials</h3> +<ul> + <li><a href="http://spark-summit.org/2013">Spark Summit 2013</a> contained a training session for which + <a href="http://spark-summit.org/summit-2013/#day2">slides and videos</a> are available for free online. + The session also included <a href="http://spark-summit.org/2013/exercises/">exercises</a> that you can run on Amazon EC2.</li> + <li>The <a href="https://amplab.cs.berkeley.edu/">UC Berkeley AMPLab</a> regularly hosts training camps on Spark and related projects. +Slides and videos are available online: <ul> - <li><a href="http://spark-summit.org/2013">Spark Summit 2013</a> was held in downtown San Francisco in December 2013. Slides and Videos of all talks are available for free. Look for links next to talk titles on the event agenda.</li> + <li><a href="http://ampcamp.berkeley.edu/3/">AMP Camp Three</a> (Berkeley, CA, August 2013)</li> + <li><a href="http://ampcamp.berkeley.edu/amp-camp-two-strata-2013/">AMP Camp Two</a> (Strata Santa Clara, February 2013)</li> + <li><a href="http://ampcamp.berkeley.edu/agenda-2012/">AMP Camp One</a> (Berkeley, CA, August 2012)</li> + </ul> + </li> </ul> -<h3>AMP Camp Slides and Videos</h3> +<h3>External Tutorials, Blog Posts, and Talks</h3> <ul> - <li>The <a href="https://amplab.cs.berkeley.edu/">UC Berkeley AMPLab</a> regularly hosts two-day training camps on Spark and related "big data" components. -Slides and videos from each camp are posted online: - <br /><a href="http://ampcamp.berkeley.edu/3/">AMP Camp Three</a> <em>Big Data Bootcamp Berkeley</em> (August 2013) - <br /><a href="http://ampcamp.berkeley.edu/amp-camp-two-strata-2013/">AMP Camp Two</a> <em>Big Data Bootcamp Strata</em> (February 2013) - <br /><a href="http://ampcamp.berkeley.edu/agenda-2012/">AMP Camp One</a> <em>Big Data Bootcamp Berkeley</em> (August 2012) - </li> + <li><a href="http://spark-summit.org/2013">Spark Summit 2013</a> — contained 30 talks about Spark use cases, available as slides and videos</li> + <li><a href="http://www.pwendell.com/2013/09/28/declarative-streams.html">Sampling Twitter Using Declarative Streams</a> — Spark Streaming tutorial by Patrick Wendell</li> + <li><a href="http://zenfractal.com/2013/08/21/a-powerful-big-data-trio/">A Powerful Big Data Trio: Spark, Parquet and Avro</a> — Using Parquet in Spark by Matt Massie</li> + <li><a href="http://www.slideshare.net/EvanChan2/cassandra2013-spark-talk-final">Real-time Analytics with Cassandra, Spark, and Shark</a> — Presentation by Evan Chan from Ooyala at 2013 Cassandra Summit</li> + <li><a href="http://syndeticlogic.net/?p=311">Getting Spark Setup in Eclipse</a> — Developer blog post by James Percent</li> + <li><a href="http://aws.amazon.com/articles/Elastic-MapReduce/4926593393724923">Run Spark and Shark on Amazon Elastic MapReduce</a> — Article by Amazon Elastic MapReduce team member Parviz Deyhim</li> + <li><a href="http://blog.quantifind.com/posts/spark-unit-test/">Unit testing with Spark</a> — Quantifind tech blog post by Imran Rashid</li> + <li><a href="http://blog.quantifind.com/posts/logging-post/">Configuring Spark logs</a> — Quantifind tech blog by Imran Rashid</li> + <li><a href="http://www.ibm.com/developerworks/library/os-spark/">Spark, an alternative for fast data analytics</a> — IBM Developer Works article by M. Tim Jones</li> </ul> <h3>Books</h3> @@ -181,27 +223,27 @@ Slides and videos from each camp are posted online: <li><a href="http://www.packtpub.com/fast-data-processing-with-spark/book">Fast Data Processing with Spark</a>, by Holden Karau (Packt Publishing)</li> </ul> -<h3>External Tutorials, Development Blogs, and Talks</h3> +<h3>Examples</h3> <ul> - <li><a href="http://www.pwendell.com/2013/09/28/declarative-streams.html">Sampling Twitter Using Declarative Streams</a> -- Spark Streaming tutorial by Patrick Wendell</li> - <li><a href="http://zenfractal.com/2013/08/21/a-powerful-big-data-trio/">A Powerful Big Data Trio: Spark, Parquet and Avro</a> -- Using Parquet in Spark by Matt Massie</li> - <li><a href="http://www.slideshare.net/EvanChan2/cassandra2013-spark-talk-final">Real-time Analytics with Cassandra, Spark, and Shark</a> -- Presentation by Evan Chan from Ooyala at the 2013 Cassandra Summit</li> - <li><a href="http://syndeticlogic.net/?p=311">Getting Spark Setup in Eclipse</a> -- Developer blog post by James Percent</li> - <li><a href="http://aws.amazon.com/articles/Elastic-MapReduce/4926593393724923">Run Spark and Shark on Amazon Elastic MapReduce</a> -- Article by Amazon AWS Elastic MapReduce team member Parviz Deyhim</li> - <li><a href="http://blog.quantifind.com/posts/spark-unit-test/">Unit testing with Spark</a> -- Quantifind tech blog post by Imran Rashid</li> - <li><a href="http://blog.quantifind.com/posts/logging-post/">Configuring Spark logs</a> -- Quantifind tech blog by Imran Rashid</li> - <li><a href="http://www.ibm.com/developerworks/library/os-spark/">Spark, an alternative for fast data analytics</a> -- IBM Developer Works article by M. Tim Jones</li> + <li>The <a href="/examples.html">Spark examples page</a> shows the basic API in Scala, Java and Python.</li> </ul> -<h3>Spark Internals</h3> +<h3>Wiki</h3> -<ul> - <li><a href="http://www.youtube.com/watch?v=49Hr5xZyTEA">Overview of Spark Internals [advanced]</a> (<a href="/talks/dev-meetup-dec-2012.pptx">pptx</a>) (<a href="http://www.youtube.com/watch?v=49Hr5xZyTEA">video</a>)</li> -</ul> +<ul><li> +The <a href="https://cwiki.apache.org/confluence/display/SPARK/Wiki+Homepage">Spark wiki</a> contains +information for developers, such as architecture documents and how to <a href="https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark">contribute</a> to Spark. +</li></ul> <h3>Research Papers</h3> +<p> +Spark was initially developed as a UC Berkeley research project, and much of the design is documented in papers. +The <a href="/research.html">research page</a> lists some of the original motivation and direction. +The following papers have been published about Spark and related projects. +</p> + <ul> <li> <a href="http://www.eecs.berkeley.edu/Pubs/TechRpts/2012/EECS-2012-214.pdf">Shark: SQL and Rich Analytics at Scale</a>. Reynold Xin, Joshua Rosen, Matei Zaharia, Michael J. Franklin, Scott Shenker, Ion Stoica. <em>Technical Report UCB/EECS-2012-214</em>. November 2012. @@ -222,25 +264,25 @@ Slides and videos from each camp are posted online: </li> </ul> - </article><!-- #post --> - - </div><!-- #content --> - - <footer id="colophon" role="contentinfo"> - <div id="site-generator"> - <p style="padding-top: 0; padding-bottom: 15px;"> - Apache Spark is an effort undergoing incubation at The Apache Software Foundation. - <a href="http://incubator.apache.org/" style="border: none;"> - <img style="vertical-align: middle; border: none;" src="/images/incubator-logo.png" alt="Apache Incubator" title="Apache Incubator" /> - </a> - </p> </div> -</footer><!-- #colophon --> +</div> + + + +<footer class="small"> + <hr> + Apache Spark is an effort undergoing incubation at The Apache Software Foundation. + <a href="http://incubator.apache.org/" style="border: none;"> + <img style="vertical-align: middle; float: right; margin-bottom: 15px;" + src="/images/incubator-logo.png" alt="Apache Incubator" title="Apache Incubator" /> + </a> +</footer> - </div><!-- #primary --> - </div><!-- #main --> -</div><!-- #page --> +</div> +<script src="https://code.jquery.com/jquery.js"></script> +<script src="//netdna.bootstrapcdn.com/bootstrap/3.0.3/js/bootstrap.min.js"></script> +<script src="/js/lang-tabs.js"></script> </body> </html> |