You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by an...@apache.org on 2013/08/23 19:28:20 UTC
svn commit: r1516940 [4/4] - in /incubator/spark/site: ./ css/ images/ news/
releases/ screencasts/ talks/
Added: incubator/spark/site/releases/spark-release-0-5-2.html
URL: http://svn.apache.org/viewvc/incubator/spark/site/releases/spark-release-0-5-2.html?rev=1516940&view=auto
==============================================================================
--- incubator/spark/site/releases/spark-release-0-5-2.html (added)
+++ incubator/spark/site/releases/spark-release-0-5-2.html Fri Aug 23 17:28:18 2013
@@ -0,0 +1,135 @@
+<!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]-->
+<head>
+ <link rel="shortcut icon" href="favicon.ico" />
+ <meta charset="UTF-8" />
+ <meta name="viewport" content="width=device-width" />
+ <title>Spark Release 0.5.2 | Spark</title>
+
+ <link rel="stylesheet" type="text/css" media="all" href="/css/style.css" />
+ <link rel="stylesheet" href="/css/pygments-default.css">
+
+ <script type="text/javascript">//<![CDATA[
+ // Google Analytics for WordPress by Yoast v4.2.8 | http://yoast.com/wordpress/google-analytics/
+ var _gaq = _gaq || [];
+ _gaq.push(['_setAccount', 'UA-32518208-1']);
+ _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>
+
+ <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>
+</head>
+
+<!--body class="page singular"-->
+<body class="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 href="/">
+ <img src="/images/spark-project-header1.png" width="1000" height="220" alt="Spark: Lightning-Fast Cluster Computing" title="Spark: Lightning-Fast Cluster Computing" />
+ </a>
+
+ <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 ">
+ <a href="/documentation.html">Documentation</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/examples.html">Examples</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/mailing-lists.html">Mailing Lists</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/research.html">Research</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/faq.html">FAQ</a>
+ </li>
+
+ </ul></div>
+ </nav><!-- #access -->
+</header><!-- #branding -->
+
+
+
+ <div id="main">
+ <div id="primary">
+ <div id="content" role="main">
+
+ <article class="page type-page status-publish hentry">
+ <h2>Spark Release 0.5.2</h2>
+
+
+<p>Spark 0.5.2 is a minor release, whose main addition is to allow Spark to compile against Hadoop 2 distributions. To do this, edit <code>project/SparkBuild.scala</code> and change both the <code>HADOOP_VERSION</code> and <code>HADOOP_MAJOR_VERSION</code> variables, then recompile Spark. This change was contributed by Thomas Dudziak.</p>
+
+<p>You can download Spark 0.5.2 as a <a href="https://github.com/downloads/mesos/spark/spark-0.5.2-sources.tgz">tar.gz file</a> (2 MB).</p>
+
+ </article><!-- #post -->
+
+ </div><!-- #content -->
+
+ <footer id="colophon" role="contentinfo">
+ <div id="site-generator">
+ <p>Spark is an open source project developed at the UC Berkeley <a href="https://amplab.cs.berkeley.edu">AMPLab</a>.</p>
+ <a class="amp-logo" style="background:url(/images/amplab-small.png)" href="https://amplab.cs.berkeley.edu/" title="Brought to you by the UC Berkeley AMPLab." rel="generator"><!--Brought to you by the UC Berkeley AMPLab--> </a>
+ </div>
+</footer><!-- #colophon -->
+
+ </div><!-- #primary -->
+ </div><!-- #main -->
+</div><!-- #page -->
+
+
+</body>
+</html>
Added: incubator/spark/site/releases/spark-release-0-6-0.html
URL: http://svn.apache.org/viewvc/incubator/spark/site/releases/spark-release-0-6-0.html?rev=1516940&view=auto
==============================================================================
--- incubator/spark/site/releases/spark-release-0-6-0.html (added)
+++ incubator/spark/site/releases/spark-release-0-6-0.html Fri Aug 23 17:28:18 2013
@@ -0,0 +1,210 @@
+<!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]-->
+<head>
+ <link rel="shortcut icon" href="favicon.ico" />
+ <meta charset="UTF-8" />
+ <meta name="viewport" content="width=device-width" />
+ <title>Spark Release 0.6.0 | Spark</title>
+
+ <link rel="stylesheet" type="text/css" media="all" href="/css/style.css" />
+ <link rel="stylesheet" href="/css/pygments-default.css">
+
+ <script type="text/javascript">//<![CDATA[
+ // Google Analytics for WordPress by Yoast v4.2.8 | http://yoast.com/wordpress/google-analytics/
+ var _gaq = _gaq || [];
+ _gaq.push(['_setAccount', 'UA-32518208-1']);
+ _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>
+
+ <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>
+</head>
+
+<!--body class="page singular"-->
+<body class="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 href="/">
+ <img src="/images/spark-project-header1.png" width="1000" height="220" alt="Spark: Lightning-Fast Cluster Computing" title="Spark: Lightning-Fast Cluster Computing" />
+ </a>
+
+ <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 ">
+ <a href="/documentation.html">Documentation</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/examples.html">Examples</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/mailing-lists.html">Mailing Lists</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/research.html">Research</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/faq.html">FAQ</a>
+ </li>
+
+ </ul></div>
+ </nav><!-- #access -->
+</header><!-- #branding -->
+
+
+
+ <div id="main">
+ <div id="primary">
+ <div id="content" role="main">
+
+ <article class="page type-page status-publish hentry">
+ <h2>Spark Release 0.6.0</h2>
+
+
+<p>Spark 0.6.0 is a major release that brings several new features, architectural changes, and performance enhancements. The most visible additions are a standalone deploy mode, a Java API, and expanded documentation; but there are also numerous other changes under the hood, which improve performance in some cases by as much as 2x.</p>
+
+<p>You can download this release as either a <a href="http://github.com/downloads/mesos/spark/spark-0.6.0-sources.tar.gz">source package</a> (2 MB tar.gz) or <a href="http://github.com/downloads/mesos/spark/spark-0.6.0-prebuilt.tar.gz">prebuilt package</a> (48 MB tar.gz)</p>
+
+<h3>Simpler Deployment</h3>
+
+<p>In addition to running on Mesos, Spark now has a <a href="/docs/0.6.0/spark-standalone.html">standalone deploy mode</a> that lets you quickly launch a cluster without installing an external cluster manager. The standalone mode only needs Java installed on each machine, and Spark deployed to it.</p>
+
+<p>In addition, there is <a href="/docs/0.6.0/running-on-yarn.html">experimental support for running on YARN</a> (Hadoop NextGen), currently in a separate branch.</p>
+
+<h3>Java API</h3>
+
+<p>Java programmers can now use Spark through a new <a href="/docs/0.6.0/java-programming-guide.html">Java API layer</a>. This layer makes available all of Spark’s features, including parallel transformations, distributed datasets, broadcast variables, and accumulators, in a Java-friendly manner.</p>
+
+<h3>Expanded Documentation</h3>
+
+<p>Spark’s <a href="/docs/0.6.0/">documentation</a> has been expanded with a new <a href="/docs/0.6.0/quick-start.html">quick start guide</a>, additional deployment instructions, configuration guide, tuning guide, and improved <a href="/docs/0.6.0/api/core">Scaladoc</a> API documentation.</p>
+
+<h3>Engine Changes</h3>
+
+<p>Under the hood, Spark 0.6 has new, custom storage and communication layers brought in from the upcoming <a href="http://www.cs.berkeley.edu/~matei/papers/2012/hotcloud_spark_streaming.pdf">Spark Streaming</a> project. These can improve performance over past versions by as much as 2x. Specifically:</p>
+
+<ul>
+ <li>A new communication manager using asynchronous Java NIO lets shuffle operations run faster, especially when sending large amounts of data or when jobs have many tasks.</li>
+ <li>A new storage manager supports per-dataset storage level settings (e.g. whether to keep the dataset in memory, deserialized, on disk, etc, or even replicated across nodes).</li>
+ <li>Spark's scheduler and control plane have been optimized to better support ultra-low-latency jobs (under 500ms) and high-throughput scheduling decisions.</li>
+</ul>
+
+<h3>New APIs</h3>
+
+<ul>
+ <li>This release adds the ability to control caching strategies on a per-RDD level, so that different RDDs may be stored in memory, on disk, as serialized bytes, etc. You can choose your storage level using the <a href="/docs/0.6.0/scala-programming-guide.html#rdd-persistence"><tt>persist()</tt> method</a> on RDD.</li>
+ <li>A new Accumulable class generalizes Accumulators for the case when the type being accumulated is not the same as the types of elements being added (e.g. you wish to accumulate a collection, such as a Set, by adding individual elements).</li>
+ <li>You can now dynamically add files or JARs that should be shipped to your workers with <tt>SparkContext.addFile/Jar</tt>.</li>
+ <li>More Spark operators (e.g. joins) support custom partitioners.</li>
+</ul>
+
+<h3>Enhanced Debugging</h3>
+
+<p>Spark’s log now prints which operation in your program each RDD and job described in your logs belongs to, making it easier to tie back to which parts of your code experience problems.</p>
+
+<h3>Maven Artifacts</h3>
+
+<p>Spark is now available in Maven Central, making it easier to link into your programs without having to build it as a JAR. Use the following Maven identifiers to add it to a project:</p>
+
+<ul>
+ <li>groupId: org.spark-project</li>
+ <li>artifactId: spark-core_2.9.2</li>
+ <li>version: 0.6.0</li>
+</ul>
+
+<h3>Compatibility</h3>
+
+<p>This release is source-compatible with Spark 0.5 programs, but you will need to recompile them against 0.6. In addition, the configuration for caching has changed: instead of having a <tt>spark.cache.class</tt> parameter that sets one caching strategy for all RDDs, you can now set a <a href="/docs/0.6.0/scala-programming-guide.html#rdd-persistence">per-RDD storage level</a>. Spark will warn if you try to set <tt>spark.cache.class</tt>.</p>
+
+<h3>Credits</h3>
+
+<p>Spark 0.6 was the work of a large set of new contributors from Berkeley and outside.</p>
+
+<ul>
+ <li>Tathagata Das contributed the new communication layer, and parts of the storage layer.</li>
+ <li>Haoyuan Li contributed the new storage manager.</li>
+ <li>Denny Britz contributed the YARN deploy mode, key aspects of the standalone one, and several other features.</li>
+ <li>Andy Konwinski contributed the revamped documentation site, Maven publishing, and several API docs.</li>
+ <li>Josh Rosen contributed the Java API, and several bug fixes.</li>
+ <li>Patrick Wendell contributed the enhanced debugging feature and helped with testing and documentation.</li>
+ <li>Reynold Xin contributed numerous bug and performance fixes.</li>
+ <li>Imran Rashid contributed the new Accumulable class.</li>
+ <li>Harvey Feng contributed improvements to shuffle operations.</li>
+ <li>Shivaram Venkataraman improved Spark's memory estimation and wrote a memory tuning guide.</li>
+ <li>Ravi Pandya contributed Spark run scripts for Windows.
+ </li><li>Mosharaf Chowdhury provided several fixes to broadcast.</li>
+ <li>Henry Milner pointed out several bugs in sampling algorithms.</li>
+ <li>Ray Racine provided improvements to the EC2 scripts.</li>
+ <li>Paul Ruan and Bill Zhao helped with testing.</li>
+</ul>
+
+<p style="padding-top:5px;">Thanks also to all the Spark users who have diligently suggested features or reported bugs.</p>
+
+ </article><!-- #post -->
+
+ </div><!-- #content -->
+
+ <footer id="colophon" role="contentinfo">
+ <div id="site-generator">
+ <p>Spark is an open source project developed at the UC Berkeley <a href="https://amplab.cs.berkeley.edu">AMPLab</a>.</p>
+ <a class="amp-logo" style="background:url(/images/amplab-small.png)" href="https://amplab.cs.berkeley.edu/" title="Brought to you by the UC Berkeley AMPLab." rel="generator"><!--Brought to you by the UC Berkeley AMPLab--> </a>
+ </div>
+</footer><!-- #colophon -->
+
+ </div><!-- #primary -->
+ </div><!-- #main -->
+</div><!-- #page -->
+
+
+</body>
+</html>
Added: incubator/spark/site/releases/spark-release-0-6-1.html
URL: http://svn.apache.org/viewvc/incubator/spark/site/releases/spark-release-0-6-1.html?rev=1516940&view=auto
==============================================================================
--- incubator/spark/site/releases/spark-release-0-6-1.html (added)
+++ incubator/spark/site/releases/spark-release-0-6-1.html Fri Aug 23 17:28:18 2013
@@ -0,0 +1,150 @@
+<!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]-->
+<head>
+ <link rel="shortcut icon" href="favicon.ico" />
+ <meta charset="UTF-8" />
+ <meta name="viewport" content="width=device-width" />
+ <title>Spark Release 0.6.1 | Spark</title>
+
+ <link rel="stylesheet" type="text/css" media="all" href="/css/style.css" />
+ <link rel="stylesheet" href="/css/pygments-default.css">
+
+ <script type="text/javascript">//<![CDATA[
+ // Google Analytics for WordPress by Yoast v4.2.8 | http://yoast.com/wordpress/google-analytics/
+ var _gaq = _gaq || [];
+ _gaq.push(['_setAccount', 'UA-32518208-1']);
+ _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>
+
+ <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>
+</head>
+
+<!--body class="page singular"-->
+<body class="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 href="/">
+ <img src="/images/spark-project-header1.png" width="1000" height="220" alt="Spark: Lightning-Fast Cluster Computing" title="Spark: Lightning-Fast Cluster Computing" />
+ </a>
+
+ <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 ">
+ <a href="/documentation.html">Documentation</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/examples.html">Examples</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/mailing-lists.html">Mailing Lists</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/research.html">Research</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/faq.html">FAQ</a>
+ </li>
+
+ </ul></div>
+ </nav><!-- #access -->
+</header><!-- #branding -->
+
+
+
+ <div id="main">
+ <div id="primary">
+ <div id="content" role="main">
+
+ <article class="page type-page status-publish hentry">
+ <h2>Spark Release 0.6.1</h2>
+
+
+<p>Spark 0.6.1 is a maintenance release that contains several important bug fixes and performance improvements. You can download it as a <a href="https://github.com/downloads/mesos/spark/spark-0.6.1-sources.tgz">source package</a> (2.4 MB tar.gz) or <a href="https://github.com/downloads/mesos/spark/spark-0.6.1-prebuilt.tgz">prebuilt package</a> (48 MB tar.gz).</p>
+
+<p>The fixes and improvements in this version include:</p>
+<ul>
+ <li>Fixed overly aggressive message timeouts that could cause workers to disconnect from the cluster</li>
+ <li>Fixed a bug in the standalone deploy mode that did not expose hostnames to scheduler, affecting HDFS locality</li>
+ <li>Improved connection reuse in shuffle, which can greatly speed up small shuffles (contributed by Reynold Xin)</li>
+ <li>Fixed some potential deadlocks in the block manager (contributed by Tathagata Das)</li>
+ <li>Fixed a bug getting IDs of failed hosts from Mesos (contributed by Imran Rashid)</li>
+ <li>Several EC2 script improvements, like better handling of spot instances (contributed by Josh Rosen)</li>
+ <li>Made the local IP address that Spark binds to customizable (contributed by Mikhail Bautin)</li>
+ <li>Support for Hadoop 2 distributions (contributed by Thomas Dudziak)</li>
+ <li>Support for locating Scala on Debian distributions (contributed by Thomas Dudziak)</li>
+ <li>Improved standalone cluster web UI to show more information about jobs</li>
+ <li>Added an option to spread out jobs over the standalone cluster instead of concentrating them on a small number of nodes (<code>spark.deploy.spreadOut</code>)</li>
+</ul>
+
+<p>We recommend that all Spark 0.6 users update to this maintenance release.</p>
+
+ </article><!-- #post -->
+
+ </div><!-- #content -->
+
+ <footer id="colophon" role="contentinfo">
+ <div id="site-generator">
+ <p>Spark is an open source project developed at the UC Berkeley <a href="https://amplab.cs.berkeley.edu">AMPLab</a>.</p>
+ <a class="amp-logo" style="background:url(/images/amplab-small.png)" href="https://amplab.cs.berkeley.edu/" title="Brought to you by the UC Berkeley AMPLab." rel="generator"><!--Brought to you by the UC Berkeley AMPLab--> </a>
+ </div>
+</footer><!-- #colophon -->
+
+ </div><!-- #primary -->
+ </div><!-- #main -->
+</div><!-- #page -->
+
+
+</body>
+</html>
Added: incubator/spark/site/releases/spark-release-0-6-2.html
URL: http://svn.apache.org/viewvc/incubator/spark/site/releases/spark-release-0-6-2.html?rev=1516940&view=auto
==============================================================================
--- incubator/spark/site/releases/spark-release-0-6-2.html (added)
+++ incubator/spark/site/releases/spark-release-0-6-2.html Fri Aug 23 17:28:18 2013
@@ -0,0 +1,164 @@
+<!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]-->
+<head>
+ <link rel="shortcut icon" href="favicon.ico" />
+ <meta charset="UTF-8" />
+ <meta name="viewport" content="width=device-width" />
+ <title>Spark Release 0.6.2 | Spark</title>
+
+ <link rel="stylesheet" type="text/css" media="all" href="/css/style.css" />
+ <link rel="stylesheet" href="/css/pygments-default.css">
+
+ <script type="text/javascript">//<![CDATA[
+ // Google Analytics for WordPress by Yoast v4.2.8 | http://yoast.com/wordpress/google-analytics/
+ var _gaq = _gaq || [];
+ _gaq.push(['_setAccount', 'UA-32518208-1']);
+ _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>
+
+ <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>
+</head>
+
+<!--body class="page singular"-->
+<body class="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 href="/">
+ <img src="/images/spark-project-header1.png" width="1000" height="220" alt="Spark: Lightning-Fast Cluster Computing" title="Spark: Lightning-Fast Cluster Computing" />
+ </a>
+
+ <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 ">
+ <a href="/documentation.html">Documentation</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/examples.html">Examples</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/mailing-lists.html">Mailing Lists</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/research.html">Research</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/faq.html">FAQ</a>
+ </li>
+
+ </ul></div>
+ </nav><!-- #access -->
+</header><!-- #branding -->
+
+
+
+ <div id="main">
+ <div id="primary">
+ <div id="content" role="main">
+
+ <article class="page type-page status-publish hentry">
+ <h2>Spark Release 0.6.2</h2>
+
+
+<p>Spark 0.6.2 is a maintenance release that contains several bug fixes and usability improvements. You can download it as a <a href="http://spark-project.org/files/spark-0.6.2-sources.tgz">source package</a> (2.5 MB tar.gz) or <a href="http://spark-project.org/files/spark-0.6.2-prebuilt.tgz">prebuilt package</a> (48 MB tar.gz).</p>
+
+<p>We recommend that all Spark 0.6 users update to this maintenance release.</p>
+
+<p>The fixes and improvements in this version include:</p>
+<ul>
+ <li>A number of fault tolerance fixes regarding detecting dead nodes, handling missing map output fetches, and allowing failed nodes to rejoin the cluster</li>
+ <li>Documentation fixes that clarify the configuration for the standalone mode and improve the quick start instructions</li>
+ <li>A connection reuse bug fix that improves shuffle performance</li>
+ <li>Support for launching a cluster across multiple availability zones in the EC2 scripts</li>
+ <li>Support for deleting security groups when an EC2 cluster is terminated</li>
+ <li>Improved memory configuration for the standalone deploy cluster daemons: instead of using <code>SPARK_MEM</code> for their memory, which often led people to give them much more memory than they intended, they now use a separate variable, <code>SPARK_DAEMON_MEMORY</code>, with a reasonable default of 512 MB
+ <li>Fixes to the Windows run scripts for Spark</li>
+ <li>Better detection of a machine's external IP address</li>
+ <li>Several small optimizations and bug fixes</li>
+
+
+In total, eleven people contributed to this release:
+<ul>
+ <li>Stephen Haberman (bug fix)</li>
+ <li>Shane Huang (shuffle fix)</li>
+ <li>Fernand Pajot (bug fix)</li>
+ <li>Andrew Psaltis (bug fix)</li>
+ <li>Imran Rashid (standalone cluster, bug fix)</li>
+ <li>Charles Reiss (fault recovery fixes, node re-registration, tests)</li>
+ <li>Josh Rosen (fault recovery, Java API fixes, deploy scripts)</li>
+ <li>Peter Sankauskas (EC2 scripts)</li>
+ <li>Lee Moon Soo (bug fix)</li>
+ <li>Patrick Wendell (bugs, docs)</li>
+ <li>Matei Zaharia (fault recovery, UI, docs, bug fixes)</li>
+</ul>
+</li></ul>
+
+ </article><!-- #post -->
+
+ </div><!-- #content -->
+
+ <footer id="colophon" role="contentinfo">
+ <div id="site-generator">
+ <p>Spark is an open source project developed at the UC Berkeley <a href="https://amplab.cs.berkeley.edu">AMPLab</a>.</p>
+ <a class="amp-logo" style="background:url(/images/amplab-small.png)" href="https://amplab.cs.berkeley.edu/" title="Brought to you by the UC Berkeley AMPLab." rel="generator"><!--Brought to you by the UC Berkeley AMPLab--> </a>
+ </div>
+</footer><!-- #colophon -->
+
+ </div><!-- #primary -->
+ </div><!-- #main -->
+</div><!-- #page -->
+
+
+</body>
+</html>
Added: incubator/spark/site/releases/spark-release-0-7-0.html
URL: http://svn.apache.org/viewvc/incubator/spark/site/releases/spark-release-0-7-0.html?rev=1516940&view=auto
==============================================================================
--- incubator/spark/site/releases/spark-release-0-7-0.html (added)
+++ incubator/spark/site/releases/spark-release-0-7-0.html Fri Aug 23 17:28:18 2013
@@ -0,0 +1,232 @@
+<!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]-->
+<head>
+ <link rel="shortcut icon" href="favicon.ico" />
+ <meta charset="UTF-8" />
+ <meta name="viewport" content="width=device-width" />
+ <title>Spark Release 0.7.0 | Spark</title>
+
+ <link rel="stylesheet" type="text/css" media="all" href="/css/style.css" />
+ <link rel="stylesheet" href="/css/pygments-default.css">
+
+ <script type="text/javascript">//<![CDATA[
+ // Google Analytics for WordPress by Yoast v4.2.8 | http://yoast.com/wordpress/google-analytics/
+ var _gaq = _gaq || [];
+ _gaq.push(['_setAccount', 'UA-32518208-1']);
+ _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>
+
+ <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>
+</head>
+
+<!--body class="page singular"-->
+<body class="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 href="/">
+ <img src="/images/spark-project-header1.png" width="1000" height="220" alt="Spark: Lightning-Fast Cluster Computing" title="Spark: Lightning-Fast Cluster Computing" />
+ </a>
+
+ <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 ">
+ <a href="/documentation.html">Documentation</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/examples.html">Examples</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/mailing-lists.html">Mailing Lists</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/research.html">Research</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/faq.html">FAQ</a>
+ </li>
+
+ </ul></div>
+ </nav><!-- #access -->
+</header><!-- #branding -->
+
+
+
+ <div id="main">
+ <div id="primary">
+ <div id="content" role="main">
+
+ <article class="page type-page status-publish hentry">
+ <h2>Spark Release 0.7.0</h2>
+
+
+<p>The Spark team is proud to release version 0.7.0, a new major release that brings several new features. Most notable are a <a href="/docs/0.7.0/python-programming-guide.html">Python API for Spark</a> and an <a href="/docs/0.7.0/streaming-programming-guide.html">alpha of Spark Streaming</a>. (Details on Spark Streaming can also be found in this <a href="http://www.eecs.berkeley.edu/Pubs/TechRpts/2012/EECS-2012-259.pdf">technical report</a>.) The release also adds numerous other improvements across the board. Overall, this is our biggest release to date, with 31 contributors, of which 20 were external to Berkeley.</p>
+
+<p>You can download Spark 0.7.0 as either a <a href="/files/spark-0.7.0-sources.tgz">source package</a> (4 MB tar.gz) or <a href="/files/spark-0.7.0-prebuilt.tgz">prebuilt package</a> (60 MB tar.gz).</p>
+
+<h3>Python API</h3>
+
+<p>Spark 0.7 adds a <a href="/docs/0.7.0/python-programming-guide.html">Python API</a> called PySpark that makes it possible to use Spark from Python, both in standalone programs and in interactive Python shells. It uses the standard CPython runtime, so your programs can call into native libraries like NumPy and SciPy. Like the Scala and Java APIs, PySpark will automatically ship functions from your main program, along with the variables they depend on, to the cluster. PySpark supports most Spark features, including RDDs, accumulators, broadcast variables, and HDFS input and output.</p>
+
+<h3>Spark Streaming Alpha</h3>
+
+<p>Spark Streaming is a new extension of Spark that adds near-real-time processing capability. It offers a simple and high-level API, where users can transform streams using parallel operations like <tt>map</tt>, <tt>filter</tt>, <tt>reduce</tt>, and new sliding window functions. It automatically distributes work over a cluster and provides efficient fault recovery with exactly-once semantics for transformations, without relying on costly transactions to an external system. Spark Streaming is described in more detail in <a href="/talks/strata_spark_streaming.ppt">these slides</a> and <a href="http://www.eecs.berkeley.edu/Pubs/TechRpts/2012/EECS-2012-259.pdf">our technical report</a>. This release is our first alpha of Spark Streaming, with most of the functionality implemented and APIs in Java and Scala.</p>
+
+<h3>Memory Dashboard</h3>
+
+<p>Spark jobs now launch a web dashboard for monitoring the memory usage of each distributed dataset (RDD) in the program. Look for lines like this in your log:</p>
+
+<p><tt>15:08:44 INFO BlockManagerUI: Started BlockManager web UI at http://mbk.local:63814</tt></p>
+
+<p>You can also control which port to use through the <tt>spark.ui.port</tt> property.</p>
+
+<h3>Maven Build</h3>
+
+<p>Spark can now be built using Maven in addition to SBT. The Maven build enables easier publishing to repositories of your choice, easy selection of Hadoop versions using the Maven profile (<tt>-Phadoop1</tt> or <tt>-Phadoop2</tt>), as well as Debian packaging using <tt>mvn -Phadoop1,deb install</tt>.</p>
+
+<h3>New Operations</h3>
+
+<p>This release adds several RDD transformations, including <tt>keys</tt>, <tt>values</tt>, <tt>keyBy</tt>, <tt>subtract</tt>, <tt>coalesce</tt>, <tt>zip</tt>. It also adds <tt>SparkContext.hadoopConfiguration</tt> to allow programs to configure Hadoop input/output settings globally across operations. Finally, it adds the <tt>RDD.toDebugString()</tt> method, which can be used to print an RDD’s lineage graph for troubleshooting.</p>
+
+<h3>EC2 Improvements</h3>
+
+<ul>
+ <li>Spark will now read S3 credentials from the <tt>AWS_ACCESS_KEY_ID</tt> and <tt>AWS_SECRET_ACCESS_KEY</tt> environment variables, if set, making it easier to access Amazon S3.</li>
+ <li>This release fixes a bug with S3 access that would leave streams open when they are not fully read (e.g. when calling <tt>RDD.first()</tt> or a SQL query with a limit), causing nodes to hang.</li>
+ <li>The EC2 scripts now support both standalone and Mesos clusters, and launch Ganglia on the cluster.</li>
+ <li>Spark EC2 clusters can now be spread across multiple availability zones.</li>
+</ul>
+
+<h3>Other Improvements</h3>
+
+<ul>
+ <li>Shuffle operations like <tt>groupByKey</tt> and <tt>reduceByKey</tt> now try to infer parallelism from the size of the parent RDD (unless <tt>spark.default.parallelism</tt> is set).</li>
+ <li>Several performance improvements to shuffles.</li>
+ <li>Standalone deploy cluster now spreads jobs out across machines by default, leading to better data locality.</li>
+ <li>Better error reporting when jobs aren't being launched due to not enough resources.</li>
+ <li>Standalone deploy web UI now includes JSON endpoints for querying cluster state.</li>
+ <li>Better support for IBM JVM.</li>
+ <li>Default Hadoop version dependency updated to 1.0.4.</li>
+ <li>Improved failure handling and reporting of error messages.</li>
+ <li>Separate configuration for standalone cluster daemons and user applications.</li>
+ <li>Significant refactoring of the scheduler codebase to enable richer unit testing.</li>
+ <li>Several bug and performance fixes throughout.</li>
+</ul>
+
+<h3>Compatibility</h3>
+
+<p>This release is API-compatible with Spark 0.6 programs, but the following features changed slightly:</p>
+<ul>
+ <li>Parallel shuffle operations where you don't specify a level of parallelism use the number of partitions of the parent RDD instead of a constant default. However, if you set <tt>spark.default.parallelism</tt>, they will use that.</li>
+ <li><tt>SparkContext.addFile</tt>, which distributes a file to worker nodes, is no longer guaranteed to put it in the executor's working directory---instead, you can find the directory it used using <tt>SparkFiles.getRootDirectory</tt>, or get a particular file using <tt>SparkFiles.get</tt>. This was done to avoid cluttering the local directory when running in local mode.</li>
+</ul>
+
+<h3>Credits</h3>
+
+<p>Spark 0.7 was the work of many contributors from Berkeley and outside—in total, 31 different contributors, of which 20 were from outside Berkeley. Here are the people who contributed, along with areas they worked on:</p>
+
+<ul>
+ <li>Mikhail Bautin -- Maven build</li>
+ <li>Denny Britz -- memory dashboard, streaming, bug fixes</li>
+ <li>Paul Cavallaro -- error reporting</li>
+ <li>Tathagata Das -- streaming (lead developer), 24/7 operation, bug fixes, docs</li>
+ <li>Thomas Dudziak -- Maven build, Hadoop 2 support</li>
+ <li>Harvey Feng -- bug fix</li>
+ <li>Stephen Haberman -- new RDD operations, configuration, S3 improvements, code cleanup, bug fixes</li>
+ <li>Tyson Hamilton -- JSON status endpoints</li>
+ <li>Mark Hamstra -- API improvements, docs</li>
+ <li>Michael Heuer -- docs</li>
+ <li>Shane Huang -- shuffle performance fixes</li>
+ <li>Andy Konwinski -- docs</li>
+ <li>Ryan LeCompte -- streaming</li>
+ <li>Haoyuan Li -- streaming</li>
+ <li>Richard McKinley -- build</li>
+ <li>Sean McNamara -- streaming</li>
+ <li>Lee Moon Soo -- bug fix</li>
+ <li>Fernand Pajot -- bug fix</li>
+ <li>Nick Pentreath -- Python API, examples</li>
+ <li>Andrew Psaltis -- bug fixes</li>
+ <li>Imran Rashid -- memory dashboard, bug fixes</li>
+ <li>Charles Reiss -- fault recovery fixes, code cleanup, testability, error reporting</li>
+ <li>Josh Rosen -- Python API (lead developer), EC2 scripts, bug fixes</li>
+ <li>Peter Sankauskas -- EC2 scripts</li>
+ <li>Prashant Sharma -- streaming</li>
+ <li>Shivaram Venkataraman -- EC2 scripts, optimizations</li>
+ <li>Patrick Wendell -- streaming, bug fixes, examples, docs</li>
+ <li>Reynold Xin -- optimizations, UI</li>
+ <li>Haitao Yao -- run scripts</li>
+ <li>Matei Zaharia -- streaming, fault recovery, Python API, code cleanup, bug fixes, docs</li>
+ <li>Eric Zhang -- examples</li>
+</ul>
+
+<p>Thanks to everyone who contributed!</p>
+
+ </article><!-- #post -->
+
+ </div><!-- #content -->
+
+ <footer id="colophon" role="contentinfo">
+ <div id="site-generator">
+ <p>Spark is an open source project developed at the UC Berkeley <a href="https://amplab.cs.berkeley.edu">AMPLab</a>.</p>
+ <a class="amp-logo" style="background:url(/images/amplab-small.png)" href="https://amplab.cs.berkeley.edu/" title="Brought to you by the UC Berkeley AMPLab." rel="generator"><!--Brought to you by the UC Berkeley AMPLab--> </a>
+ </div>
+</footer><!-- #colophon -->
+
+ </div><!-- #primary -->
+ </div><!-- #main -->
+</div><!-- #page -->
+
+
+</body>
+</html>
Added: incubator/spark/site/releases/spark-release-0-7-2.html
URL: http://svn.apache.org/viewvc/incubator/spark/site/releases/spark-release-0-7-2.html?rev=1516940&view=auto
==============================================================================
--- incubator/spark/site/releases/spark-release-0-7-2.html (added)
+++ incubator/spark/site/releases/spark-release-0-7-2.html Fri Aug 23 17:28:18 2013
@@ -0,0 +1,174 @@
+<!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]-->
+<head>
+ <link rel="shortcut icon" href="favicon.ico" />
+ <meta charset="UTF-8" />
+ <meta name="viewport" content="width=device-width" />
+ <title>Spark Release 0.7.2 | Spark</title>
+
+ <link rel="stylesheet" type="text/css" media="all" href="/css/style.css" />
+ <link rel="stylesheet" href="/css/pygments-default.css">
+
+ <script type="text/javascript">//<![CDATA[
+ // Google Analytics for WordPress by Yoast v4.2.8 | http://yoast.com/wordpress/google-analytics/
+ var _gaq = _gaq || [];
+ _gaq.push(['_setAccount', 'UA-32518208-1']);
+ _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>
+
+ <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>
+</head>
+
+<!--body class="page singular"-->
+<body class="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 href="/">
+ <img src="/images/spark-project-header1.png" width="1000" height="220" alt="Spark: Lightning-Fast Cluster Computing" title="Spark: Lightning-Fast Cluster Computing" />
+ </a>
+
+ <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 ">
+ <a href="/documentation.html">Documentation</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/examples.html">Examples</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/mailing-lists.html">Mailing Lists</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/research.html">Research</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/faq.html">FAQ</a>
+ </li>
+
+ </ul></div>
+ </nav><!-- #access -->
+</header><!-- #branding -->
+
+
+
+ <div id="main">
+ <div id="primary">
+ <div id="content" role="main">
+
+ <article class="page type-page status-publish hentry">
+ <h2>Spark Release 0.7.2</h2>
+
+
+<p>Spark 0.7.2 is a maintenance release that contains multiple bug fixes and improvements. You can download it as a <a href="http://spark-project.org/download-spark-0.7.2-sources">source package</a> (4 MB tar.gz) or get prebuilt packages for <a href="http://spark-project.org/download-spark-0.7.2-prebuilt-hadoop1">Hadoop 1 / CDH3</a> or <a href="http://spark-project.org/download-spark-0.7.2-prebuilt-cdh4">CDH 4</a> (61 MB tar.gz).</p>
+
+<p>We recommend that all users update to this maintenance release.</p>
+
+<p>The fixes and improvements in this version include:</p>
+<ul>
+ <li>Scala version updated to 2.9.3.</li>
+ <li>Several improvements to Bagel, including performance fixes and a configurable storage level.</li>
+ <li>New API methods: subtractByKey, foldByKey, mapWith, filterWith, foreachPartition, and others.</li>
+ <li>A new metrics reporting interface, SparkListener, to collect information about each computation stage: task lengths, bytes shuffled, etc.</li>
+ <li>Several new examples using the Java API, including K-means and computing pi.</li>
+ <li>Support for launching multiple worker instances per host in the standalone mode.</li>
+ <li>Various bug fixes across the board.</li>
+</ul>
+
+<p>The following people contributed to this release:</p>
+<ul>
+ <li>Jey Kottalam (Maven build, bug fixes, EC2 scripts, packaging the release)</li>
+ <li>Andrew Ash (bug fixes, docs)</li>
+ <li>Andrey Kouznetsov (bug fixes)</li>
+ <li>Andy Konwinski (docs)</li>
+ <li>Charles Reiss (bug fixes)</li>
+ <li>Christoph Grothaus (bug fixes)</li>
+ <li>Erik van Oosten (bug fixes)</li>
+ <li>Giovanni Delussu (bug fixes)</li>
+ <li>Hiral Patel (bug fixes)</li>
+ <li>Holden Karau (error reporting, EC2 scripts)</li>
+ <li>Imran Rashid (metrics reporting system)</li>
+ <li>Josh Rosen (EC2 scripts)</li>
+ <li>Mark Hamstra (new API methods, tests)</li>
+ <li>Mikhail Bautin (build)</li>
+ <li>Mosharaf Chowdhury (bug fixes)</li>
+ <li>Nick Pentreath (Bagel, examples)</li>
+ <li>Patrick Wendell (bug fixes)</li>
+ <li>Reynold Xin (bug fixes)</li>
+ <li>Stephen Haberman (bug fixes, tests, subtractByKey)</li>
+ <li>Kalpit Shah (build, multiple workers per host)</li>
+ <li>Mike Potts (run scripts)</li>
+ <li>Matei Zaharia (Bagel, bug fixes, build)</li>
+</ul>
+
+<p>We thank everyone who helped with this release, and hope to see more contributions from you in the future!</p>
+
+ </article><!-- #post -->
+
+ </div><!-- #content -->
+
+ <footer id="colophon" role="contentinfo">
+ <div id="site-generator">
+ <p>Spark is an open source project developed at the UC Berkeley <a href="https://amplab.cs.berkeley.edu">AMPLab</a>.</p>
+ <a class="amp-logo" style="background:url(/images/amplab-small.png)" href="https://amplab.cs.berkeley.edu/" title="Brought to you by the UC Berkeley AMPLab." rel="generator"><!--Brought to you by the UC Berkeley AMPLab--> </a>
+ </div>
+</footer><!-- #colophon -->
+
+ </div><!-- #primary -->
+ </div><!-- #main -->
+</div><!-- #page -->
+
+
+</body>
+</html>
Added: incubator/spark/site/releases/spark-release-0-7-3.html
URL: http://svn.apache.org/viewvc/incubator/spark/site/releases/spark-release-0-7-3.html?rev=1516940&view=auto
==============================================================================
--- incubator/spark/site/releases/spark-release-0-7-3.html (added)
+++ incubator/spark/site/releases/spark-release-0-7-3.html Fri Aug 23 17:28:18 2013
@@ -0,0 +1,168 @@
+<!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]-->
+<head>
+ <link rel="shortcut icon" href="favicon.ico" />
+ <meta charset="UTF-8" />
+ <meta name="viewport" content="width=device-width" />
+ <title>Spark Release 0.7.3 | Spark</title>
+
+ <link rel="stylesheet" type="text/css" media="all" href="/css/style.css" />
+ <link rel="stylesheet" href="/css/pygments-default.css">
+
+ <script type="text/javascript">//<![CDATA[
+ // Google Analytics for WordPress by Yoast v4.2.8 | http://yoast.com/wordpress/google-analytics/
+ var _gaq = _gaq || [];
+ _gaq.push(['_setAccount', 'UA-32518208-1']);
+ _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>
+
+ <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>
+</head>
+
+<!--body class="page singular"-->
+<body class="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 href="/">
+ <img src="/images/spark-project-header1.png" width="1000" height="220" alt="Spark: Lightning-Fast Cluster Computing" title="Spark: Lightning-Fast Cluster Computing" />
+ </a>
+
+ <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 ">
+ <a href="/documentation.html">Documentation</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/examples.html">Examples</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/mailing-lists.html">Mailing Lists</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/research.html">Research</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/faq.html">FAQ</a>
+ </li>
+
+ </ul></div>
+ </nav><!-- #access -->
+</header><!-- #branding -->
+
+
+
+ <div id="main">
+ <div id="primary">
+ <div id="content" role="main">
+
+ <article class="page type-page status-publish hentry">
+ <h2>Spark Release 0.7.3</h2>
+
+
+<p>Spark 0.7.3 is a maintenance release with several bug fixes, performance fixes, and new features. You can download it as a <a href="/download/spark-0.7.3-sources.tgz">source package</a> (4 MB tar.gz) or get prebuilt packages for <a href="/download/spark-0.7.3-prebuilt-hadoop1.tgz">Hadoop 1 / CDH3</a> or for <a href="/download/spark-0.7.3-prebuilt-cdh4.tgz">CDH 4</a> (61 MB tar.gz).</p>
+
+<p>We recommend that all users update to this maintenance release.</p>
+
+<p>The improvements in this release include:</p>
+
+<ul>
+ <li><b>New "add JARs" functionality in Spark shell:</b> Users of <code>spark-shell</code> can now set the <code>ADD_JARS</code> environment variable to add a list of JARs to their clusters; these will also be sent to workers.</li>
+ <li><b>Windows fixes:</b> Spark standalone clusters now properly kill executors when a job ends or fails. In addition, adding JAR paths with backslashes will now work correctly.</li>
+ <li><b>Streaming API fixes:</b> The Kafka and Twitter APIs for Spark Streaming have been updated. In the Twitter case, this is to deal with the username/password authentication method being disabled in by Twitter, while in the Kafka case, it is to allow receiving messages other than strings. Note that these are breaking API changes as the Streaming API is still in alpha.</li>
+ <li><b>Python performance:</b> Spark's mechanism for spawning Python VMs has been improved to do so faster when the JVM has a large heap size, speeding up the Python API.</li>
+ <li><b>Mesos fixes:</b> JARs added to your job will now be on the classpath when deserializing task results in Mesos.</li>
+ <li><b>Error reporting:</b> Better error reporting for non-serializable exceptions and overly large task results.</li>
+ <li><b>Examples:</b> Added an example of stateful stream processing with <code>updateStateByKey</code>.</li>
+ <li><b>Build:</b> Spark Streaming no longer depends on the Twitter4J repo, which should allow it to build in China.</li>
+ <li><b>Bug fixes</b> in <code>foldByKey</code>, streaming <code>count</code>, statistics methods, documentation, and web UI.</li>
+</ul>
+
+<p>The following people contributed to this release:</p>
+
+<ul>
+ <li>Charles Reiss (Mesos)</li>
+ <li>Christoph Grothaus (Windows spawn fixes)</li>
+ <li>Christopher Nguyen (bug fixes)</li>
+ <li>James Phillpotts (Twitter input stream)</li>
+ <li>Jey Kottalam (Python performance)</li>
+ <li>Josh Rosen (usability)</li>
+ <li>Konstantin Boudnik (build)</li>
+ <li>Mark Hamstra (build)</li>
+ <li>Matei Zaharia (Windows, docs, ADD_JARS, Python, streaming)</li>
+ <li>Patrick Wendell (usability)</li>
+ <li>Tathagata Das (streaming fixes)</li>
+ <li>Jerry Shao (bug fixes)</li>
+ <li>S. Kumar (examples)</li>
+ <li>Sean McNamara (Kafka input streams, streaming fixes)</li>
+</ul>
+
+ </article><!-- #post -->
+
+ </div><!-- #content -->
+
+ <footer id="colophon" role="contentinfo">
+ <div id="site-generator">
+ <p>Spark is an open source project developed at the UC Berkeley <a href="https://amplab.cs.berkeley.edu">AMPLab</a>.</p>
+ <a class="amp-logo" style="background:url(/images/amplab-small.png)" href="https://amplab.cs.berkeley.edu/" title="Brought to you by the UC Berkeley AMPLab." rel="generator"><!--Brought to you by the UC Berkeley AMPLab--> </a>
+ </div>
+</footer><!-- #colophon -->
+
+ </div><!-- #primary -->
+ </div><!-- #main -->
+</div><!-- #page -->
+
+
+</body>
+</html>
Added: incubator/spark/site/research.html
URL: http://svn.apache.org/viewvc/incubator/spark/site/research.html?rev=1516940&view=auto
==============================================================================
--- incubator/spark/site/research.html (added)
+++ incubator/spark/site/research.html Fri Aug 23 17:28:18 2013
@@ -0,0 +1,174 @@
+<!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]-->
+<head>
+ <link rel="shortcut icon" href="favicon.ico" />
+ <meta charset="UTF-8" />
+ <meta name="viewport" content="width=device-width" />
+ <title>Research | Spark</title>
+
+ <link rel="stylesheet" type="text/css" media="all" href="/css/style.css" />
+ <link rel="stylesheet" href="/css/pygments-default.css">
+
+ <script type="text/javascript">//<![CDATA[
+ // Google Analytics for WordPress by Yoast v4.2.8 | http://yoast.com/wordpress/google-analytics/
+ var _gaq = _gaq || [];
+ _gaq.push(['_setAccount', 'UA-32518208-1']);
+ _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>
+
+ <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>
+</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 href="/">
+ <img src="/images/spark-project-header1.png" width="1000" height="220" alt="Spark: Lightning-Fast Cluster Computing" title="Spark: Lightning-Fast Cluster Computing" />
+ </a>
+
+ <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 ">
+ <a href="/documentation.html">Documentation</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/examples.html">Examples</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/mailing-lists.html">Mailing Lists</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page current-menu-item">
+ <a href="/research.html">Research</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/faq.html">FAQ</a>
+ </li>
+
+ </ul></div>
+ </nav><!-- #access -->
+</header><!-- #branding -->
+
+
+
+ <div id="main">
+ <div id="primary">
+ <div id="content" role="main">
+
+ <article class="page type-page status-publish hentry">
+ <h2>Spark Research</h2>
+
+<p>
+Spark started as a research project at UC Berkeley in the <a href="https://amplab.cs.berkeley.edu">AMPLab</a>, which focuses on big data analytics.
+</p>
+
+<p class="noskip">
+Our goal was to design a programming model that supports a much wider class of applications than MapReduce, while maintaining its automatic fault tolerance. In particular, MapReduce is inefficient for <em>multi-pass</em> applications that require low-latency data sharing across multiple parallel operations. These applications are quite common in analytics, and include:
+</p>
+
+<ul>
+ <li><em>Iterative algorithms</em>, including many machine learning algorithms and graph algorithms like PageRank.</li>
+ <li><em>Interactive data mining</em>, where a user would like to load data into RAM across a cluster and query it repeatedly.</li>
+ <li><em>OLAP reports</em> that run multiple aggregation queries on the same data.</li>
+</ul>
+
+<p>
+MapReduce and Dryad are suboptimal for these applications because they are based on acyclic data flow: an application has to run as a series of distinct jobs, each of which reads data from stable storage (e.g. a distributed file system) and writes it back to stable storage. They incur significant cost loading the data on each step and writing it back to replicated storage.
+</p>
+
+<p>
+Spark offers an abstraction called <a href="http://www.cs.berkeley.edu/~matei/papers/2012/nsdi_spark.pdf"><em>resilient distributed datasets (RDDs)</em></a> to support these applications efficiently. RDDs can be stored in memory between queries <em>without</em> requiring replication. Instead, they rebuild lost data on failure using <em>lineage</em>: each RDD remembers how it was built from other datasets (by transformations like <em>map</em>, <em>join</em> or <em>group-by</em>) to rebuild itself. RDDs allow Spark to outperform existing models by up to 100x in multi-pass analytics. We showed that RDDs can support a wide variety of iterative algorithms, as well as interactive data mining and a highly efficient SQL engine (the <a href="http://shark.cs.berkeley.edu">Shark</a> project).
+</p>
+
+<p class="noskip">You can find more about the research behind Spark in our papers:</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.
+ </li>
+ <li>
+ <a href="http://www.cs.berkeley.edu/~matei/papers/2012/hotcloud_spark_streaming.pdf">Discretized Streams: An Efficient and Fault-Tolerant Model for Stream Processing on Large Clusters</a>. Matei Zaharia, Tathagata Das, Haoyuan Li, Scott Shenker, Ion Stoica. <em>HotCloud 2012</em>. June 2012.
+ </li>
+ <li>
+ <a href="http://www.cs.berkeley.edu/~matei/papers/2012/sigmod_shark_demo.pdf">Shark: Fast Data Analysis Using Coarse-grained Distributed Memory</a> (demo). Cliff Engle, Antonio Lupher, Reynold Xin, Matei Zaharia, Haoyuan Li, Scott Shenker, Ion Stoica. <em>SIGMOD 2012</em>. May 2012. <b>Best Demo Award</b>.
+ </li>
+ <li>
+ <a href="http://www.cs.berkeley.edu/~matei/papers/2012/nsdi_spark.pdf">Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing</a>. Matei Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy McCauley, Michael J. Franklin, Scott Shenker, Ion Stoica. <em>NSDI 2012</em>. April 2012. <b>Best Paper Award</b> and <b>Honorable Mention for Community Award</b>.
+ </li>
+ <li>
+ <a href="http://www.cs.berkeley.edu/~matei/papers/2011/tr_spark.pdf">Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing</a>. Matei Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy McCauley, Michael J. Franklin, Scott Shenker, Ion Stoica. <em>Technical Report UCB/EECS-2011-82</em>. July 2011.</li>
+ <li>
+ <a href="http://www.cs.berkeley.edu/~matei/papers/2010/hotcloud_spark.pdf">Spark: Cluster Computing with Working Sets</a>. Matei Zaharia, Mosharaf Chowdhury, Michael J. Franklin, Scott Shenker, Ion Stoica. <em>HotCloud 2010</em>. June 2010.
+ </li>
+</ul>
+
+ </article><!-- #post -->
+
+ </div><!-- #content -->
+
+ <footer id="colophon" role="contentinfo">
+ <div id="site-generator">
+ <p>Spark is an open source project developed at the UC Berkeley <a href="https://amplab.cs.berkeley.edu">AMPLab</a>.</p>
+ <a class="amp-logo" style="background:url(/images/amplab-small.png)" href="https://amplab.cs.berkeley.edu/" title="Brought to you by the UC Berkeley AMPLab." rel="generator"><!--Brought to you by the UC Berkeley AMPLab--> </a>
+ </div>
+</footer><!-- #colophon -->
+
+ </div><!-- #primary -->
+ </div><!-- #main -->
+</div><!-- #page -->
+
+
+</body>
+</html>
Added: incubator/spark/site/screencasts/1-first-steps-with-spark.html
URL: http://svn.apache.org/viewvc/incubator/spark/site/screencasts/1-first-steps-with-spark.html?rev=1516940&view=auto
==============================================================================
--- incubator/spark/site/screencasts/1-first-steps-with-spark.html (added)
+++ incubator/spark/site/screencasts/1-first-steps-with-spark.html Fri Aug 23 17:28:18 2013
@@ -0,0 +1,145 @@
+<!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]-->
+<head>
+ <link rel="shortcut icon" href="favicon.ico" />
+ <meta charset="UTF-8" />
+ <meta name="viewport" content="width=device-width" />
+ <title>First Steps with Spark - Screencast #1 | Spark</title>
+
+ <link rel="stylesheet" type="text/css" media="all" href="/css/style.css" />
+ <link rel="stylesheet" href="/css/pygments-default.css">
+
+ <script type="text/javascript">//<![CDATA[
+ // Google Analytics for WordPress by Yoast v4.2.8 | http://yoast.com/wordpress/google-analytics/
+ var _gaq = _gaq || [];
+ _gaq.push(['_setAccount', 'UA-32518208-1']);
+ _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>
+
+ <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>
+</head>
+
+<!--body class="page singular"-->
+<body class="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 href="/">
+ <img src="/images/spark-project-header1.png" width="1000" height="220" alt="Spark: Lightning-Fast Cluster Computing" title="Spark: Lightning-Fast Cluster Computing" />
+ </a>
+
+ <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 ">
+ <a href="/documentation.html">Documentation</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/examples.html">Examples</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/mailing-lists.html">Mailing Lists</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/research.html">Research</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/faq.html">FAQ</a>
+ </li>
+
+ </ul></div>
+ </nav><!-- #access -->
+</header><!-- #branding -->
+
+
+
+ <div id="main">
+ <div id="primary">
+ <div id="content" role="main">
+
+ <article class="page type-page status-publish hentry">
+ <h2>First Steps with Spark - Screencast #1</h2>
+
+
+This screencast marks the beginning of a series of hands-on screencasts we will be publishing to help new users get up and running in minutes. In this screencast, we:
+<ol>
+ <li>Download and build Spark on a local machine (running OS X, but should be a similar process for Linux or Unix).</li>
+ <li>Introduce the API using the Spark interactive shell to explore a file.</li>
+</ol>
+
+<div class="video-container shadow"><iframe width="755" height="705" src="http://www.youtube.com/embed/KYlLglXD6Ic?autohide=0&showinfo=0" frameborder="0" allowfullscreen></iframe></div>
+
+Check out the next spark screencast in the series, <a href="/screencasts/2-spark-documentation-overview.html">Spark Screencast #2 - Overview of Spark Documentation</a>. You can also find the Spark documentation online:
+<ul>
+ <li><a href="/documentation.html">Spark documentation page</a></li>
+ <li><a href="http://ampcamp.berkeley.edu/big-data-mini-course-home">Amp Camp Mini Course</a></li>
+</ul>
+
+ </article><!-- #post -->
+
+ </div><!-- #content -->
+
+ <footer id="colophon" role="contentinfo">
+ <div id="site-generator">
+ <p>Spark is an open source project developed at the UC Berkeley <a href="https://amplab.cs.berkeley.edu">AMPLab</a>.</p>
+ <a class="amp-logo" style="background:url(/images/amplab-small.png)" href="https://amplab.cs.berkeley.edu/" title="Brought to you by the UC Berkeley AMPLab." rel="generator"><!--Brought to you by the UC Berkeley AMPLab--> </a>
+ </div>
+</footer><!-- #colophon -->
+
+ </div><!-- #primary -->
+ </div><!-- #main -->
+</div><!-- #page -->
+
+
+</body>
+</html>
Added: incubator/spark/site/screencasts/2-spark-documentation-overview.html
URL: http://svn.apache.org/viewvc/incubator/spark/site/screencasts/2-spark-documentation-overview.html?rev=1516940&view=auto
==============================================================================
--- incubator/spark/site/screencasts/2-spark-documentation-overview.html (added)
+++ incubator/spark/site/screencasts/2-spark-documentation-overview.html Fri Aug 23 17:28:18 2013
@@ -0,0 +1,141 @@
+<!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]-->
+<head>
+ <link rel="shortcut icon" href="favicon.ico" />
+ <meta charset="UTF-8" />
+ <meta name="viewport" content="width=device-width" />
+ <title>Spark Documentation Overview â Screencast #2 | Spark</title>
+
+ <link rel="stylesheet" type="text/css" media="all" href="/css/style.css" />
+ <link rel="stylesheet" href="/css/pygments-default.css">
+
+ <script type="text/javascript">//<![CDATA[
+ // Google Analytics for WordPress by Yoast v4.2.8 | http://yoast.com/wordpress/google-analytics/
+ var _gaq = _gaq || [];
+ _gaq.push(['_setAccount', 'UA-32518208-1']);
+ _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>
+
+ <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>
+</head>
+
+<!--body class="page singular"-->
+<body class="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 href="/">
+ <img src="/images/spark-project-header1.png" width="1000" height="220" alt="Spark: Lightning-Fast Cluster Computing" title="Spark: Lightning-Fast Cluster Computing" />
+ </a>
+
+ <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 ">
+ <a href="/documentation.html">Documentation</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/examples.html">Examples</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/mailing-lists.html">Mailing Lists</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/research.html">Research</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/faq.html">FAQ</a>
+ </li>
+
+ </ul></div>
+ </nav><!-- #access -->
+</header><!-- #branding -->
+
+
+
+ <div id="main">
+ <div id="primary">
+ <div id="content" role="main">
+
+ <article class="page type-page status-publish hentry">
+ <h2>Spark Documentation Overview â Screencast #2</h2>
+
+
+This is our 2nd Spark screencast. In it, we take a tour of the documentation available for Spark users online.
+
+<div class="video-container shadow"><iframe width="755" height="705" src="http://www.youtube.com/embed/TikdEfsrFnw?autohide=0&showinfo=0" frameborder="0" allowfullscreen></iframe></div>
+
+And for convenience, here are links to the documentation shown in the video:
+<ul>
+ <li><a href="/documentation.html">Spark documentation page</a></li>
+ <li><a href="http://ampcamp.berkeley.edu/big-data-mini-course-home">Amp Camp Mini Course</a></li>
+</ul>
+
+ </article><!-- #post -->
+
+ </div><!-- #content -->
+
+ <footer id="colophon" role="contentinfo">
+ <div id="site-generator">
+ <p>Spark is an open source project developed at the UC Berkeley <a href="https://amplab.cs.berkeley.edu">AMPLab</a>.</p>
+ <a class="amp-logo" style="background:url(/images/amplab-small.png)" href="https://amplab.cs.berkeley.edu/" title="Brought to you by the UC Berkeley AMPLab." rel="generator"><!--Brought to you by the UC Berkeley AMPLab--> </a>
+ </div>
+</footer><!-- #colophon -->
+
+ </div><!-- #primary -->
+ </div><!-- #main -->
+</div><!-- #page -->
+
+
+</body>
+</html>
Added: incubator/spark/site/screencasts/3-transformations-and-caching.html
URL: http://svn.apache.org/viewvc/incubator/spark/site/screencasts/3-transformations-and-caching.html?rev=1516940&view=auto
==============================================================================
--- incubator/spark/site/screencasts/3-transformations-and-caching.html (added)
+++ incubator/spark/site/screencasts/3-transformations-and-caching.html Fri Aug 23 17:28:18 2013
@@ -0,0 +1,137 @@
+<!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]-->
+<head>
+ <link rel="shortcut icon" href="favicon.ico" />
+ <meta charset="UTF-8" />
+ <meta name="viewport" content="width=device-width" />
+ <title>Transformations and Caching - Spark Screencast #3 | Spark</title>
+
+ <link rel="stylesheet" type="text/css" media="all" href="/css/style.css" />
+ <link rel="stylesheet" href="/css/pygments-default.css">
+
+ <script type="text/javascript">//<![CDATA[
+ // Google Analytics for WordPress by Yoast v4.2.8 | http://yoast.com/wordpress/google-analytics/
+ var _gaq = _gaq || [];
+ _gaq.push(['_setAccount', 'UA-32518208-1']);
+ _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>
+
+ <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>
+</head>
+
+<!--body class="page singular"-->
+<body class="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 href="/">
+ <img src="/images/spark-project-header1.png" width="1000" height="220" alt="Spark: Lightning-Fast Cluster Computing" title="Spark: Lightning-Fast Cluster Computing" />
+ </a>
+
+ <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 ">
+ <a href="/documentation.html">Documentation</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/examples.html">Examples</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/mailing-lists.html">Mailing Lists</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/research.html">Research</a>
+ </li>
+
+ <li class="menu-item menu-item-type-post_type menu-item-object-page ">
+ <a href="/faq.html">FAQ</a>
+ </li>
+
+ </ul></div>
+ </nav><!-- #access -->
+</header><!-- #branding -->
+
+
+
+ <div id="main">
+ <div id="primary">
+ <div id="content" role="main">
+
+ <article class="page type-page status-publish hentry">
+ <h2>Transformations and Caching - Spark Screencast #3</h2>
+
+
+In this third Spark screencast, we demonstrate more advanced use of RDD actions and transformations, as well as caching RDDs in memory.
+
+<div class="video-container shadow"><iframe width="755" height="705" src="http://www.youtube.com/embed/T1lZcimvL18?autohide=0&showinfo=0" frameborder="0" allowfullscreen></iframe></div>
+
+For more information, check out the <a href="/documentation.html">Spark documentation page</a>.
+
+ </article><!-- #post -->
+
+ </div><!-- #content -->
+
+ <footer id="colophon" role="contentinfo">
+ <div id="site-generator">
+ <p>Spark is an open source project developed at the UC Berkeley <a href="https://amplab.cs.berkeley.edu">AMPLab</a>.</p>
+ <a class="amp-logo" style="background:url(/images/amplab-small.png)" href="https://amplab.cs.berkeley.edu/" title="Brought to you by the UC Berkeley AMPLab." rel="generator"><!--Brought to you by the UC Berkeley AMPLab--> </a>
+ </div>
+</footer><!-- #colophon -->
+
+ </div><!-- #primary -->
+ </div><!-- #main -->
+</div><!-- #page -->
+
+
+</body>
+</html>
Added: incubator/spark/site/talks/overview.pdf
URL: http://svn.apache.org/viewvc/incubator/spark/site/talks/overview.pdf?rev=1516940&view=auto
==============================================================================
Binary file - no diff available.
Propchange: incubator/spark/site/talks/overview.pdf
------------------------------------------------------------------------------
svn:mime-type = application/octet-stream
Added: incubator/spark/site/talks/overview.pptx
URL: http://svn.apache.org/viewvc/incubator/spark/site/talks/overview.pptx?rev=1516940&view=auto
==============================================================================
Binary file - no diff available.
Propchange: incubator/spark/site/talks/overview.pptx
------------------------------------------------------------------------------
svn:mime-type = application/octet-stream
Added: incubator/spark/site/talks/strata_spark_streaming.pdf
URL: http://svn.apache.org/viewvc/incubator/spark/site/talks/strata_spark_streaming.pdf?rev=1516940&view=auto
==============================================================================
Binary file - no diff available.
Propchange: incubator/spark/site/talks/strata_spark_streaming.pdf
------------------------------------------------------------------------------
svn:mime-type = application/octet-stream
Added: incubator/spark/site/talks/strata_spark_streaming.ppt
URL: http://svn.apache.org/viewvc/incubator/spark/site/talks/strata_spark_streaming.ppt?rev=1516940&view=auto
==============================================================================
Binary file - no diff available.
Propchange: incubator/spark/site/talks/strata_spark_streaming.ppt
------------------------------------------------------------------------------
svn:mime-type = application/octet-stream