http://git-wip-us.apache.org/repos/asf/flink-web/blob/a16dddeb/content/news/2014/01/28/querying_mongodb.html ---------------------------------------------------------------------- diff --git a/content/news/2014/01/28/querying_mongodb.html b/content/news/2014/01/28/querying_mongodb.html new file mode 100644 index 0000000..a081d09 --- /dev/null +++ b/content/news/2014/01/28/querying_mongodb.html @@ -0,0 +1,375 @@ +<!DOCTYPE html> +<html lang="en"> + <head> + <meta charset="utf-8"> + <meta http-equiv="X-UA-Compatible" content="IE=edge"> + <meta name="viewport" content="width=device-width, initial-scale=1"> + + <title>Apache Flink: Accessing Data Stored in MongoDB with Stratosphere</title> + <link rel="shortcut icon" href="favicon.ico" type="image/x-icon"> + <link rel="icon" href="favicon.ico" type="image/x-icon"> + <link rel="stylesheet" href="/css/bootstrap.css"> + <link rel="stylesheet" href="/css/bootstrap-lumen-custom.css"> + <link rel="stylesheet" href="/css/syntax.css"> + <link rel="stylesheet" href="/css/custom.css"> + <link href="/css/main/main.css" rel="stylesheet"> + <link href="/blog/feed.xml" rel="alternate" type="application/rss+xml" title="Flink Blog RSS feed" /> + <!-- <link href="//maxcdn.bootstrapcdn.com/font-awesome/4.1.0/css/font-awesome.min.css" rel="stylesheet"> --> + <script src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.0/jquery.min.js";></script> + <script src="/js/bootstrap.min.js"></script> + <script src="/js/codetabs.js"></script> + </head> + <body> + <div class="af-header-container af-inner-pages-navigation"> + <header> + <div class="container"> + <div class="row"> + <div class="col-md-1 af-mobile-nav-bar"> + <a href="/" title="Home"> + <img class="hidden-xs hidden-sm img-responsive" + src="/img/main/logo.png" alt="Apache Flink Logo"> + </a> + <div class="row visible-xs"> + <div class="col-xs-3"> + <a href="/" title="Home"> + <img class="hidden-x hidden-sm img-responsive" + src="/img/main/logo.png" alt="Apache Flink Logo"> + </a> + </div> + <div class="col-xs-5"></div> + <div class="col-xs-4"> + <div class="af-mobile-btn"> + <span class="glyphicon glyphicon-plus"></span> + </div> + </div> + </div> + </div> + <!-- Navigation --> + <div class="col-md-11"> + <nav class="af-main-nav" role="navigation"> + <ul> + <li><a href="#" class="af-nav-links">Quickstart + <b class="caret"></b> + </a> + <ul class="af-dropdown-menu"> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/setup_quickstart.html";>Setup + Flink</a></li> + <li><a + href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/java_api_quickstart.html";>Java + API</a></li> + <li><a + href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/scala_api_quickstart.html";>Scala + API</a></li> + </ul></li> + <li><a href="/downloads.html">Download</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/faq.html";>FAQ</a></li> + <li><a href="#" class="af-nav-links">Documentation <b + class="caret"></b></a> + <ul class="af-dropdown-menu"> + <li class="af-separator">Current Snapshot:</li> + <li></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-master/";>0.9</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-master/api/java";>0.9 Javadocs</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-master/api/scala/index.html#org.apache.flink.api.scala.package";>0.9 Scaladocs</a></li> + <li class="divider"></li> + <li class="af-separator">Current Stable:</li> + <li></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/";>0.8.1</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/api/java";>0.8.1 Javadocs</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/api/scala/index.html#org.apache.flink.api.scala.package";>0.8.1 Scaladocs</a></li> + <li class="divider"></li> + <li></li> + <li><a href="/archive.html">Archive</a></li> + <li></li> + </ul></li> + <li><a href="#" class="af-nav-links">Community <b + class="caret"></b></a> + <ul class="af-dropdown-menu"> + <li><a href="/community.html#getting-help">Getting Help</a></li> + <li><a href="/community.html#mailing-lists">Mailing Lists</a></li> + <li><a href="/community.html#issues">Issues</a></li> + <li><a href="/community.html#team">Team</a></li> + <li class="divider"></li> + <li><a href="/how-to-contribute.html">How To + Contribute</a></li> + <li><a href="/coding_guidelines.html">Coding + Guidelines</a></li> + </ul></li> + <li><a href="#" class="af-nav-links">Project <b + class="caret"></b></a> + <ul class="af-dropdown-menu"> + <li><a href="/material.html">Material</a></li> + <li><a href="http://www.apache.org/";>Apache Software + Foundation <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a + href="https://cwiki.apache.org/confluence/display/FLINK";>Wiki + <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a + href="https://wiki.apache.org/incubator/StratosphereProposal";>Incubator + Proposal <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a href="http://www.apache.org/licenses/LICENSE-2.0";>License + <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a href="https://github.com/apache/incubator-flink";>Source + Code <span class="glyphicon glyphicon-new-window"></span> + </a></li> + </ul></li> + <li><a href="/blog/index.html" class="">Blog</a></li> + </ul> + </nav> + </div> + </div> + </div> + </header> +</div> + + + <div style="padding-top:50px" class="container"> + <div class="container"> + <div class="row"> + <div class="col-md-2"></div> + <div class="col-md-8"> + <article> + <h2>Accessing Data Stored in MongoDB with Stratosphere</h2> + <p class="meta">28 Jan 2014</p> + <div> + <p>We recently merged a <a href="https://github.com/stratosphere/stratosphere/pull/437";>pull request</a> that allows you to use any existing Hadoop <a href="http://developer.yahoo.com/hadoop/tutorial/module5.html#inputformat";>InputFormat</a> with Stratosphere. So you can now (in the <code>0.5-SNAPSHOT</code> and upwards versions) define a Hadoop-based data source:</p> +<div class="highlight"><pre><code class="language-java" data-lang="java"><span class="n">HadoopDataSource</span> <span class="n">source</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">HadoopDataSource</span><span class="o">(</span><span class="k">new</span> <span class="nf">TextInputFormat</span><span class="o">(),</span> <span class="k">new</span> <span class="nf">JobConf</span><span class="o">(),</span> <span class="s">"Input Lines"</span><span class="o">);</span> +<span class="n">TextInputFormat</span><span class="o">.</span><span class="na">addInputPath</span><span class="o">(</span><span class="n">source</span><span class="o">.</span><span class="na">getJobConf</span><span class="o">(),</span> <span class="k">new</span> <span class="nf">Path</span><span class="o">(</span><span class="n">dataInput</span><span class="o">));</span> +</code></pre></div> +<p>We describe in the following article how to access data stored in <a href="http://www.mongodb.org/";>MongoDB</a> with Stratosphere. This allows users to join data from multiple sources (e.g. MonogDB and HDFS) or perform machine learning with the documents stored in MongoDB.</p> + +<p>The approach here is to use the <code>MongoInputFormat</code> that was developed for Apache Hadoop but now also runs with Stratosphere.</p> +<div class="highlight"><pre><code class="language-java" data-lang="java"><span class="n">JobConf</span> <span class="n">conf</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">JobConf</span><span class="o">();</span> +<span class="n">conf</span><span class="o">.</span><span class="na">set</span><span class="o">(</span><span class="s">"mongo.input.uri"</span><span class="o">,</span><span class="s">"mongodb://localhost:27017/enron_mail.messages"</span><span class="o">);</span> +<span class="n">HadoopDataSource</span> <span class="n">src</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">HadoopDataSource</span><span class="o">(</span><span class="k">new</span> <span class="nf">MongoInputFormat</span><span class="o">(),</span> <span class="n">conf</span><span class="o">,</span> <span class="s">"Read from Mongodb"</span><span class="o">,</span> <span class="k">new</span> <span class="nf">WritableWrapperConverter</span><span class="o">());</span> +</code></pre></div> +<h3 id="example-program">Example Program</h3> + +<p>The example program reads data from the <a href="http://www.cs.cmu.edu/%7Eenron/";>enron dataset</a> that contains about 500k internal e-mails. The data is stored in MongoDB and the Stratosphere program counts the number of e-mails per day.</p> + +<p>The complete code of this sample program is available on <a href="https://github.com/stratosphere/stratosphere-mongodb-example";>GitHub</a>.</p> + +<h4 id="prepare-mongodb-and-the-data">Prepare MongoDB and the Data</h4> + +<ul> +<li>Install MongoDB</li> +<li>Download the enron dataset from <a href="http://mongodb-enron-email.s3-website-us-east-1.amazonaws.com/";>their website</a>.</li> +<li>Unpack and load it</li> +</ul> +<div class="highlight"><pre><code class="language-bash" data-lang="bash"> bunzip2 enron_mongo.tar.bz2 + tar xvf enron_mongo.tar + mongorestore dump/enron_mail/messages.bson +</code></pre></div> +<p>We used <a href="http://robomongo.org/";>Robomongo</a> to visually examine the dataset stored in MongoDB.</p> + +<p><img src="/img/blog/robomongo.png" style="width:90%;margin:15px"></p> + +<h4 id="build-mongoinputformat">Build <code>MongoInputFormat</code></h4> + +<p>MongoDB offers an InputFormat for Hadoop on their <a href="https://github.com/mongodb/mongo-hadoop";>GitHub page</a>. The code is not available in any Maven repository, so we have to build the jar file on our own.</p> + +<ul> +<li>Check out the repository</li> +</ul> +<div class="highlight"><pre><code class="language-text" data-lang="text">git clone https://github.com/mongodb/mongo-hadoop.git +cd mongo-hadoop +</code></pre></div> +<ul> +<li>Set the appropriate Hadoop version in the <code>build.sbt</code>, we used <code>1.1</code>.</li> +</ul> +<div class="highlight"><pre><code class="language-bash" data-lang="bash">hadoopRelease in ThisBuild :<span class="o">=</span> <span class="s2">"1.1"</span> +</code></pre></div> +<ul> +<li>Build the input format</li> +</ul> +<div class="highlight"><pre><code class="language-bash" data-lang="bash">./sbt package +</code></pre></div> +<p>The jar-file is now located in <code>core/target</code>.</p> + +<h4 id="the-stratosphere-program">The Stratosphere Program</h4> + +<p>Now we have everything prepared to run the Stratosphere program. I only ran it on my local computer, out of Eclipse. To do that, check out the code ...</p> +<div class="highlight"><pre><code class="language-bash" data-lang="bash">git clone https://github.com/stratosphere/stratosphere-mongodb-example.git +</code></pre></div> +<p>... and import it as a Maven project into your Eclipse. You have to manually add the previously built mongo-hadoop jar-file as a dependency. +You can now press the "Run" button and see how Stratosphere executes the little program. It was running for about 8 seconds on the 1.5 GB dataset.</p> + +<p>The result (located in <code>/tmp/enronCountByDay</code>) now looks like this.</p> +<div class="highlight"><pre><code class="language-text" data-lang="text">11,Fri Sep 26 10:00:00 CEST 1997 +154,Tue Jun 29 10:56:00 CEST 1999 +292,Tue Aug 10 12:11:00 CEST 1999 +185,Thu Aug 12 18:35:00 CEST 1999 +26,Fri Mar 19 12:33:00 CET 1999 +</code></pre></div> +<p>There is one thing left I want to point out here. MongoDB represents objects stored in the database as JSON-documents. Since Stratosphere's standard types do not support JSON documents, I was using the <code>WritableWrapper</code> here. This wrapper allows to use any Hadoop datatype with Stratosphere.</p> + +<p>The following code example shows how the JSON-documents are accessed in Stratosphere.</p> +<div class="highlight"><pre><code class="language-java" data-lang="java"><span class="kd">public</span> <span class="kt">void</span> <span class="nf">map</span><span class="o">(</span><span class="n">Record</span> <span class="n">record</span><span class="o">,</span> <span class="n">Collector</span><span class="o"><</span><span class="n">Record</span><span class="o">></span> <span class="n">out</span><span class="o">)</span> <span class="kd">throws</span> <span class="n">Exception</span> <span class="o">{</span> + <span class="n">Writable</span> <span class="n">valWr</span> <span class="o">=</span> <span class="n">record</span><span class="o">.</span><span class="na">getField</span><span class="o">(</span><span class="mi">1</span><span class="o">,</span> <span class="n">WritableWrapper</span><span class="o">.</span><span class="na">class</span><span class="o">).</span><span class="na">value</span><span class="o">();</span> + <span class="n">BSONWritable</span> <span class="n">value</span> <span class="o">=</span> <span class="o">(</span><span class="n">BSONWritable</span><span class="o">)</span> <span class="n">valWr</span><span class="o">;</span> + <span class="n">Object</span> <span class="n">headers</span> <span class="o">=</span> <span class="n">value</span><span class="o">.</span><span class="na">getDoc</span><span class="o">().</span><span class="na">get</span><span class="o">(</span><span class="s">"headers"</span><span class="o">);</span> + <span class="n">BasicDBObject</span> <span class="n">headerOb</span> <span class="o">=</span> <span class="o">(</span><span class="n">BasicDBObject</span><span class="o">)</span> <span class="n">headers</span><span class="o">;</span> + <span class="n">String</span> <span class="n">date</span> <span class="o">=</span> <span class="o">(</span><span class="n">String</span><span class="o">)</span> <span class="n">headerOb</span><span class="o">.</span><span class="na">get</span><span class="o">(</span><span class="s">"Date"</span><span class="o">);</span> + <span class="c1">// further date processing</span> +<span class="o">}</span> +</code></pre></div> +<p>Please use the comments if you have questions or if you want to showcase your own MongoDB-Stratosphere integration. +<br><br> +<small>Written by Robert Metzger (<a href="https://twitter.com/rmetzger_";>@rmetzger_</a>).</small></p> + + </div> + </article> + </div> + <div class="col-md-2"></div> + </div> + <div class="row" style="padding-top:30px"> + <div class="col-md-2"></div> + <div class="col-md-8"> + <div id="disqus_thread"></div> + <script type="text/javascript"> + /* * * CONFIGURATION VARIABLES: EDIT BEFORE PASTING INTO YOUR WEBPAGE * * */ + var disqus_shortname = 'stratosphere-eu'; // required: replace example with your forum shortname + + /* * * DON'T EDIT BELOW THIS LINE * * */ + (function() { + var dsq = document.createElement('script'); dsq.type = 'text/javascript'; dsq.async = true; + dsq.src = '//' + disqus_shortname + '.disqus.com/embed.js'; + (document.getElementsByTagName('head')[0] || document.getElementsByTagName('body')[0]).appendChild(dsq); + })(); + </script> + <noscript>Please enable JavaScript to view the <a href="http://disqus.com/?ref_noscript";>comments powered by Disqus.</a></noscript> + <a href="http://disqus.com"; class="dsq-brlink">comments powered by <span class="logo-disqus">Disqus</span></a> + </div> + <div class="col-md-2"></div> + </div> +</div> + + </div> + <!--<section id="af-upfooter" class="af-section"> + <div class="container"> + <p>Apache Flink is an effort undergoing incubation at The Apache + Software Foundation (ASF), sponsored by the Apache Incubator PMC. + Incubation is required of all newly accepted projects until a further + review indicates that the infrastructure, communications, and + decision making process have stabilized in a manner consistent with + other successful ASF projects. While incubation status is not + necessarily a reflection of the completeness or stability of the + code, it does indicate that the project has yet to be fully endorsed + by the ASF.</p> + <a href="http://incubator.apache.org";> <img class="img-responsive" + src="/img/main/apache-incubator-logo.png" alt="Apache Flink" /> + </a> + <p class="text-center"> + <a href="/privacy-policy.html" title="Privacy Policy" + class="af-privacy-policy">Privacy Policy</a> + </p> + </div> +</section>--> + +<footer id="af-footer"> + <div class="container"> + <div class="row"> + <div class="col-md-3"> + <h3>Documentation</h3> + <ul class="af-footer-menu"> + + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/";>0.8.1</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/api/java/";>0.8.1 Javadocs</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/api/scala/index.html#org.apache.flink.api.scala.package";>0.8.1 Scaladocs</a></li> + </ul> + </div> + <div class="col-md-3"> + <h3>Community</h3> + <ul class="af-footer-menu"> + <li><a href="/community.html#mailing-lists">Mailing Lists</a></li> + <li><a href="https://issues.apache.org/jira/browse/FLINK"; + target="blank">Issues <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="/community.html#team">Team</a></li> + <li><a href="/how-to-contribute.html">How to contribute</a></li> + <li><a href="/coding_guidelines.html">Coding Guidelines</a></li> + </ul> + </div> + <div class="col-md-3"> + <h3>ASF</h3> + <ul class="af-footer-menu"> + <li><a href="http://www.apache.org/"; target="blank">Apache + Software foundation <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a + href="http://www.apache.org/foundation/how-it-works.html"; + target="blank">How it works <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="http://www.apache.org/foundation/thanks.html"; + target="blank">Thanks <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a + href="http://www.apache.org/foundation/sponsorship.html"; + target="blank">Become a sponsor <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="http://incubator.apache.org/projects/flink.html"; + target="blank">Incubation status page <span + class="glyphicon glyphicon-new-window"></span></a></li> + </ul> + </div> + <div class="col-md-3"> + <h3>Project</h3> + <ul class="af-footer-menu"> + <li><a href="/material.html" target="blank">Material <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a + href="https://cwiki.apache.org/confluence/display/FLINK"; + target="blank">Wiki <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a + href="https://wiki.apache.org/incubator/StratosphereProposal"; + target="blank">Incubator proposal <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="http://www.apache.org/licenses/LICENSE-2.0"; + target="blank">License <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="https://github.com/apache/incubator-flink"; + target="blank">Source code <span + class="glyphicon glyphicon-new-window"></span></a></li> + </ul> + </div> + </div> + </div> + <div class="af-footer-bar"> + <div class="container"> + <p>Copyright © 2014-2015, <a href="http://www.apache.org";>The Apache Software Foundation</a>. All Rights Reserved. Apache and the Apache feather logo are trademarks of the Apache Software Foundation. + </p> + <div> + <div style="float:left"> + <p> + <a href="/privacy-policy.html" title="Privacy Policy" class="af-privacy-policy">Privacy Policy</a> + </p> + </div> + <div style="float:right"> + <p> + <a href="/blog/feed.xml" class="af-privacy-policy">RSS Feed</a> + </p> + </div> + </div> + </div> + </div> +</footer> + + <!-- Google Analytics --> + <script> + (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ + (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), + m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) + })(window,document,'script','//www.google-analytics.com/analytics.js','ga'); + + ga('create', 'UA-52545728-1', 'auto'); + ga('send', 'pageview'); + </script> + <script src="/js/main/jquery.mobile.events.min.js"></script> + <script src="/js/main/main.js"></script> + </body> +</html>
http://git-wip-us.apache.org/repos/asf/flink-web/blob/a16dddeb/content/news/2014/02/18/amazon-elastic-mapreduce-cloud-yarn.html ---------------------------------------------------------------------- diff --git a/content/news/2014/02/18/amazon-elastic-mapreduce-cloud-yarn.html b/content/news/2014/02/18/amazon-elastic-mapreduce-cloud-yarn.html new file mode 100644 index 0000000..2a9f637 --- /dev/null +++ b/content/news/2014/02/18/amazon-elastic-mapreduce-cloud-yarn.html @@ -0,0 +1,482 @@ +<!DOCTYPE html> +<html lang="en"> + <head> + <meta charset="utf-8"> + <meta http-equiv="X-UA-Compatible" content="IE=edge"> + <meta name="viewport" content="width=device-width, initial-scale=1"> + + <title>Apache Flink: Use Stratosphere with Amazon Elastic MapReduce</title> + <link rel="shortcut icon" href="favicon.ico" type="image/x-icon"> + <link rel="icon" href="favicon.ico" type="image/x-icon"> + <link rel="stylesheet" href="/css/bootstrap.css"> + <link rel="stylesheet" href="/css/bootstrap-lumen-custom.css"> + <link rel="stylesheet" href="/css/syntax.css"> + <link rel="stylesheet" href="/css/custom.css"> + <link href="/css/main/main.css" rel="stylesheet"> + <link href="/blog/feed.xml" rel="alternate" type="application/rss+xml" title="Flink Blog RSS feed" /> + <!-- <link href="//maxcdn.bootstrapcdn.com/font-awesome/4.1.0/css/font-awesome.min.css" rel="stylesheet"> --> + <script src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.0/jquery.min.js";></script> + <script src="/js/bootstrap.min.js"></script> + <script src="/js/codetabs.js"></script> + </head> + <body> + <div class="af-header-container af-inner-pages-navigation"> + <header> + <div class="container"> + <div class="row"> + <div class="col-md-1 af-mobile-nav-bar"> + <a href="/" title="Home"> + <img class="hidden-xs hidden-sm img-responsive" + src="/img/main/logo.png" alt="Apache Flink Logo"> + </a> + <div class="row visible-xs"> + <div class="col-xs-3"> + <a href="/" title="Home"> + <img class="hidden-x hidden-sm img-responsive" + src="/img/main/logo.png" alt="Apache Flink Logo"> + </a> + </div> + <div class="col-xs-5"></div> + <div class="col-xs-4"> + <div class="af-mobile-btn"> + <span class="glyphicon glyphicon-plus"></span> + </div> + </div> + </div> + </div> + <!-- Navigation --> + <div class="col-md-11"> + <nav class="af-main-nav" role="navigation"> + <ul> + <li><a href="#" class="af-nav-links">Quickstart + <b class="caret"></b> + </a> + <ul class="af-dropdown-menu"> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/setup_quickstart.html";>Setup + Flink</a></li> + <li><a + href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/java_api_quickstart.html";>Java + API</a></li> + <li><a + href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/scala_api_quickstart.html";>Scala + API</a></li> + </ul></li> + <li><a href="/downloads.html">Download</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/faq.html";>FAQ</a></li> + <li><a href="#" class="af-nav-links">Documentation <b + class="caret"></b></a> + <ul class="af-dropdown-menu"> + <li class="af-separator">Current Snapshot:</li> + <li></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-master/";>0.9</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-master/api/java";>0.9 Javadocs</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-master/api/scala/index.html#org.apache.flink.api.scala.package";>0.9 Scaladocs</a></li> + <li class="divider"></li> + <li class="af-separator">Current Stable:</li> + <li></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/";>0.8.1</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/api/java";>0.8.1 Javadocs</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/api/scala/index.html#org.apache.flink.api.scala.package";>0.8.1 Scaladocs</a></li> + <li class="divider"></li> + <li></li> + <li><a href="/archive.html">Archive</a></li> + <li></li> + </ul></li> + <li><a href="#" class="af-nav-links">Community <b + class="caret"></b></a> + <ul class="af-dropdown-menu"> + <li><a href="/community.html#getting-help">Getting Help</a></li> + <li><a href="/community.html#mailing-lists">Mailing Lists</a></li> + <li><a href="/community.html#issues">Issues</a></li> + <li><a href="/community.html#team">Team</a></li> + <li class="divider"></li> + <li><a href="/how-to-contribute.html">How To + Contribute</a></li> + <li><a href="/coding_guidelines.html">Coding + Guidelines</a></li> + </ul></li> + <li><a href="#" class="af-nav-links">Project <b + class="caret"></b></a> + <ul class="af-dropdown-menu"> + <li><a href="/material.html">Material</a></li> + <li><a href="http://www.apache.org/";>Apache Software + Foundation <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a + href="https://cwiki.apache.org/confluence/display/FLINK";>Wiki + <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a + href="https://wiki.apache.org/incubator/StratosphereProposal";>Incubator + Proposal <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a href="http://www.apache.org/licenses/LICENSE-2.0";>License + <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a href="https://github.com/apache/incubator-flink";>Source + Code <span class="glyphicon glyphicon-new-window"></span> + </a></li> + </ul></li> + <li><a href="/blog/index.html" class="">Blog</a></li> + </ul> + </nav> + </div> + </div> + </div> + </header> +</div> + + + <div style="padding-top:50px" class="container"> + <div class="container"> + <div class="row"> + <div class="col-md-2"></div> + <div class="col-md-8"> + <article> + <h2>Use Stratosphere with Amazon Elastic MapReduce</h2> + <p class="meta">18 Feb 2014</p> + <div> + <div class="lead">Get started with Stratosphere within 10 minutes using Amazon Elastic MapReduce.</div> + +<p>This step-by-step tutorial will guide you through the setup of Stratosphere using Amazon Elastic MapReduce.</p> + +<h3 id="background">Background</h3> + +<p><a href="http://aws.amazon.com/elasticmapreduce/";>Amazon Elastic MapReduce</a> (Amazon EMR) is part of Amazon Web services. EMR allows to create Hadoop clusters that analyze data stored in Amazon S3 (AWS' cloud storage). Stratosphere runs on top of Hadoop using the <a href="http://hadoop.apache.org/docs/r2.2.0/hadoop-project-dist/hadoop-common/releasenotes.html";>recently</a> released cluster resource manager <a href="http://hadoop.apache.org/docs/current2/hadoop-yarn/hadoop-yarn-site/YARN.html";>YARN</a>. YARN allows to use many different data analysis tools in your cluster side by side. Tools that run with YARN are, for example <a href="https://giraph.apache.org/";>Apache Giraph</a>, <a href="http://spark.incubator.apache.org/";>Spark</a> or <a href="http://hortonworks.com/blog/introducing-hoya-hbase-on-yarn/";>HBase</a>. Stratosphere also <a href="/docs/0.4/setup/yarn.html">runs on YARN</a> and that's the approach for this tutorial.</p> + +<h3 id="1.-step:-login-to-aws-and-prepare-secure-access">1. Step: Login to AWS and prepare secure access</h3> + +<ul> +<li>Log in to the <a href="https://console.aws.amazon.com/console/home";>AWS Console</a></li> +</ul> + +<p>You need to have SSH keys to access the Hadoop master node. If you do not have keys for your computer, generate them:</p> + +<div class="row" style="padding-top:15px"> + <div class="col-md-6"> +<a data-lightbox="inputs" href="/img/blog/emr-security.png" data-lightbox="example-1"><img class="img-responsive" src="/img/blog/emr-security.png" /></a> + </div> + <div class="col-md-6"> + <ul> + <li>Select <a href="https://console.aws.amazon.com/ec2/v2/home";>EC2</a> and click on "Key Pairs" in the "NETWORK & SECURITY" section.</li> + <li>Click on "Create Key Pair" and give it a name</li> + <li>After pressing "Yes" it will download a .pem file.</li> + <li>Change the permissions of the .pem file</li> + +<div class="highlight"><pre><code class="language-bash" data-lang="bash">chmod og-rwx ~/work-laptop.pem</code></pre></div> + + </ul> + </div> +</div> + +<h3 id="2.-step:-create-your-hadoop-cluster-in-the-cloud">2. Step: Create your Hadoop Cluster in the cloud</h3> + +<ul> +<li>Select <a href="https://console.aws.amazon.com/elasticmapreduce/vnext/";>Elastic MapReduce</a> from the AWS console</li> +<li>Click the blue "Create cluster" button.</li> +</ul> + +<div class="row" style="padding-top:15px"> + <div class="col-md-6"> +<a data-lightbox="inputs" href="/img/blog/emr-hadoopversion.png" data-lightbox="example-1"><img class="img-responsive" src="/img/blog/emr-hadoopversion.png" /></a> + </div> + <div class="col-md-6"> + <ul> + <li>Choose a Cluster name</li> + <li>You can let the other settings remain unchanged (termination protection, logging, debugging)</li> + <li>For the Hadoop distribution, it is very important to choose one with YARN support. We use <b>3.0.3 (Hadoop 2.2.0)</b> (the minor version might change over time)</li> + <li>Remove all applications to be installed (unless you want to use them)</li> + <li>Choose the instance types you want to start. Stratosphere runs fine with m1.large instances. Core and Task instances both run Stratosphere, but only core instances contain HDFS data nodes.</li> + <li>Choose the <b>EC2 key pair</b> you've created in the previous step!</li> + </ul> + </div> +</div> + +<ul> +<li>Thats it! You can now press the "Create cluster" button at the end of the form to boot it!</li> +</ul> + +<h3 id="3.-step:-launch-stratosphere">3. Step: Launch Stratosphere</h3> + +<p>You might need to wait a few minutes until Amazon started your cluster. (You can monitor the progress of the instances in EC2). Use the refresh button in the top right corner.</p> + +<p>You see that the master is up if the field <b>Master public DNS</b> contains a value (first line), connect to it using SSH.</p> + +<div class="highlight"><pre><code class="language-bash" data-lang="bash">ssh hadoop@<your master public DNS> -i <path to your .pem> +<span class="c"># for my example, it looks like this:</span> +ssh had...@ec2-54-213-61-105.us-west-2.compute.amazonaws.com -i ~/Downloads/work-laptop.pem</code></pre></div> + + + +(Windows users have to follow <a href="http://docs.aws.amazon.com/ElasticMapReduce/latest/DeveloperGuide/emr-connect-master-node-ssh.html";>these instructions</a> to SSH into the machine running the master.) </br></br> +Once connected to the master, download and start Stratosphere for YARN: +<ul> + <li>Download and extract Stratosphere-YARN</li> + +<div class="highlight"><pre><code class="language-bash" data-lang="bash">wget http://stratosphere-bin.s3-website-us-east-1.amazonaws.com/stratosphere-dist-0.5-SNAPSHOT-yarn.tar.gz +<span class="c"># extract it</span> +tar xvzf stratosphere-dist-0.5-SNAPSHOT-yarn.tar.gz</code></pre></div> + + <li>Start Stratosphere in the cluster using Hadoop YARN</li> + + +<div class="highlight"><pre><code class="language-bash" data-lang="bash"><span class="nb">cd </span>stratosphere-yarn-0.5-SNAPSHOT/ +./bin/yarn-session.sh -n <span class="m">4</span> -jm <span class="m">1024</span> -tm 3000</code></pre></div> + + +The arguments have the following meaning + <ul> + <li><code>-n</code> number of TaskManagers (=workers). This number must not exeed the number of task instances</li> + <li><code>-jm</code> memory (heapspace) for the JobManager</li> + <li><code>-tm</code> memory for the TaskManagers</li> + </ul> +</ul> + +Once the output has changed from + +<div class="highlight"><pre><code class="language-bash" data-lang="bash">JobManager is now running on N/A:6123</code></pre></div> + +to + +<div class="highlight"><pre><code class="language-bash" data-lang="bash">JobManager is now running on ip-172-31-13-68.us-west-2.compute.internal:6123</code></pre></div> + +Stratosphere has started the JobManager. It will take a few seconds until the TaskManagers (workers) have connected to the JobManager. To see how many TaskManagers connected, you have to access the JobManager's web interface. Follow the steps below to do that ... + + + + +<h3> 4. Step: Launch a Stratosphere Job</h3> + +This step shows how to submit and monitor a Stratosphere Job in the Amazon Cloud. + +<ul> +<li> Open an additional terminal and connect again to the master of your cluster. </li> + +We recommend to create a SOCKS-proxy with your SSH that allows you to easily connect into the cluster. (If you've already a VPN setup with EC2, you can probably use that as well.) + + +<div class="highlight"><pre><code class="language-bash" data-lang="bash">ssh -D localhost:2001 hadoop@<your master dns name> -i <your pem file></code></pre></div> + + +Notice the <code>-D localhost:2001</code> argument: It opens a SOCKS proxy on your computer allowing any application to use it to communicate through the proxy via an SSH tunnel to the master node. This allows you to access all services in your EMR cluster, such as the HDFS NameNode or the YARN web interface. + +<li>Configure a browser to use the SOCKS proxy. Open a browser with SOCKS proxy support (such as Firefox). Ideally, do not use your primary browser for this, since ALL traffic will be routed through Amazon.</li> + +<div class="row" style="padding-top:15px"> + <div class="col-md-6"> +<a data-lightbox="inputs" href="/img/blog/emr-firefoxsettings.png" data-lightbox="example-1"><img class="img-responsive" src="/img/blog/emr-firefoxsettings.png" /></a> + </div> + <div class="col-md-6"> + <ul> + <li>To configure the SOCKS proxy with Firefox, click on "Edit", "Preferences", choose the "Advanced" tab and press the "Settings ..." button.</li> + <li>Enter the details of the SOCKS proxy <b>localhost:2001</b>. Choose SOCKS v4.</li> + <li>Close the settings, your browser is now talking to the master node of your cluster</li> + </ul> + </div> +</div> + +<p></ul></p> + +<p>Since you're connected to the master now, you can open several web interfaces: <br> +<b>YARN Resource Manager</b>: <code>http://<masterIPAddress>:9026/</code> <br> +<b>HDFS NameNode</b>: <code>http://<masterIPAddress>:9101/</code></p> + +<p>You find the <code>masterIPAddress</code> by entering <code>ifconfig</code> into the terminal:</p> + +<div class="highlight"><pre><code class="language-bash" data-lang="bash"><span class="o">[</span>hadoop@ip-172-31-38-95 ~<span class="o">]</span><span class="nv">$ </span>ifconfig +eth0 Link encap:Ethernet HWaddr 02:CF:8E:CB:28:B2 + inet addr:172.31.38.95 Bcast:172.31.47.255 Mask:255.255.240.0 + inet6 addr: fe80::cf:8eff:fecb:28b2/64 Scope:Link + RX bytes:166314967 <span class="o">(</span>158.6 MiB<span class="o">)</span> TX bytes:89319246 <span class="o">(</span>85.1 MiB<span class="o">)</span></code></pre></div> + +<p><strong>Optional:</strong> If you want to use the hostnames within your Firefox (that also makes the NameNode links work), you have to enable DNS resolution over the SOCKS proxy. Open the Firefox config <code>about:config</code> and set <code>network.proxy.socks_remote_dns</code> to <code>true</code>.</p> + +<p>The YARN ResourceManager also allows you to connect to <b>Stratosphere's JobManager web interface</b>. Click the <b>ApplicationMaster</b> link in the "Tracking UI" column.</p> + +<p>To run the Wordcount example, you have to upload some sample data.</p> + +<div class="highlight"><pre><code class="language-bash" data-lang="bash"><span class="c"># download a text</span> +wget http://www.gnu.org/licenses/gpl.txt +<span class="c"># upload it to HDFS:</span> +hadoop fs -copyFromLocal gpl.txt /input</code></pre></div> + +<p>To run a Job, enter the following command into the master's command line:</p> + +<div class="highlight"><pre><code class="language-bash" data-lang="bash"><span class="c"># optional: go to the extracted directory</span> +<span class="nb">cd </span>stratosphere-yarn-0.5-SNAPSHOT/ +<span class="c"># run the wordcount example</span> +./bin/stratosphere run -w -j examples/stratosphere-java-examples-0.5-SNAPSHOT-WordCount.jar -a <span class="m">16</span> hdfs:///input hdfs:///output</code></pre></div> + +<p>Make sure that the number of TaskManager's have connected to the JobManager.</p> + +<p>Lets go through the command in detail:</p> + +<ul> +<li><code>./bin/stratosphere</code> is the standard launcher for Stratosphere jobs from the command line</li> +<li>The <code>-w</code> flag stands for "wait". It is a very useful to track the progress of the job.</li> +<li><code>-j examples/stratosphere-java-examples-0.5-SNAPSHOT-WordCount.jar</code> the <code>-j</code> command sets the jar file containing the job. If you have you own application, place your Jar-file here.</li> +<li><code>-a 16 hdfs:///input hdfs:///output</code> the <code>-a</code> command specifies the Job-specific arguments. In this case, the wordcount expects the following input <code><numSubStasks> <input> <output></code>.</li> +</ul> + +<p>You can monitor the progress of your job in the JobManager webinterface. Once the job has finished (which should be the case after less than 10 seconds), you can analyze it there. +Inspect the result in HDFS using:</p> + +<div class="highlight"><pre><code class="language-bash" data-lang="bash">hadoop fs -tail /output</code></pre></div> + +<p>If you want to shut down the whole cluster in the cloud, use Amazon's webinterface and click on "Terminate cluster". If you just want to stop the YARN session, press CTRL+C in the terminal. The Stratosphere instances will be killed by YARN.</p> + +<p><br><br> +<small>Written by Robert Metzger (<a href="https://twitter.com/rmetzger_";>@rmetzger_</a>).</small></p> + + </div> + </article> + </div> + <div class="col-md-2"></div> + </div> + <div class="row" style="padding-top:30px"> + <div class="col-md-2"></div> + <div class="col-md-8"> + <div id="disqus_thread"></div> + <script type="text/javascript"> + /* * * CONFIGURATION VARIABLES: EDIT BEFORE PASTING INTO YOUR WEBPAGE * * */ + var disqus_shortname = 'stratosphere-eu'; // required: replace example with your forum shortname + + /* * * DON'T EDIT BELOW THIS LINE * * */ + (function() { + var dsq = document.createElement('script'); dsq.type = 'text/javascript'; dsq.async = true; + dsq.src = '//' + disqus_shortname + '.disqus.com/embed.js'; + (document.getElementsByTagName('head')[0] || document.getElementsByTagName('body')[0]).appendChild(dsq); + })(); + </script> + <noscript>Please enable JavaScript to view the <a href="http://disqus.com/?ref_noscript";>comments powered by Disqus.</a></noscript> + <a href="http://disqus.com"; class="dsq-brlink">comments powered by <span class="logo-disqus">Disqus</span></a> + </div> + <div class="col-md-2"></div> + </div> +</div> + + </div> + <!--<section id="af-upfooter" class="af-section"> + <div class="container"> + <p>Apache Flink is an effort undergoing incubation at The Apache + Software Foundation (ASF), sponsored by the Apache Incubator PMC. + Incubation is required of all newly accepted projects until a further + review indicates that the infrastructure, communications, and + decision making process have stabilized in a manner consistent with + other successful ASF projects. While incubation status is not + necessarily a reflection of the completeness or stability of the + code, it does indicate that the project has yet to be fully endorsed + by the ASF.</p> + <a href="http://incubator.apache.org";> <img class="img-responsive" + src="/img/main/apache-incubator-logo.png" alt="Apache Flink" /> + </a> + <p class="text-center"> + <a href="/privacy-policy.html" title="Privacy Policy" + class="af-privacy-policy">Privacy Policy</a> + </p> + </div> +</section>--> + +<footer id="af-footer"> + <div class="container"> + <div class="row"> + <div class="col-md-3"> + <h3>Documentation</h3> + <ul class="af-footer-menu"> + + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/";>0.8.1</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/api/java/";>0.8.1 Javadocs</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/api/scala/index.html#org.apache.flink.api.scala.package";>0.8.1 Scaladocs</a></li> + </ul> + </div> + <div class="col-md-3"> + <h3>Community</h3> + <ul class="af-footer-menu"> + <li><a href="/community.html#mailing-lists">Mailing Lists</a></li> + <li><a href="https://issues.apache.org/jira/browse/FLINK"; + target="blank">Issues <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="/community.html#team">Team</a></li> + <li><a href="/how-to-contribute.html">How to contribute</a></li> + <li><a href="/coding_guidelines.html">Coding Guidelines</a></li> + </ul> + </div> + <div class="col-md-3"> + <h3>ASF</h3> + <ul class="af-footer-menu"> + <li><a href="http://www.apache.org/"; target="blank">Apache + Software foundation <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a + href="http://www.apache.org/foundation/how-it-works.html"; + target="blank">How it works <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="http://www.apache.org/foundation/thanks.html"; + target="blank">Thanks <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a + href="http://www.apache.org/foundation/sponsorship.html"; + target="blank">Become a sponsor <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="http://incubator.apache.org/projects/flink.html"; + target="blank">Incubation status page <span + class="glyphicon glyphicon-new-window"></span></a></li> + </ul> + </div> + <div class="col-md-3"> + <h3>Project</h3> + <ul class="af-footer-menu"> + <li><a href="/material.html" target="blank">Material <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a + href="https://cwiki.apache.org/confluence/display/FLINK"; + target="blank">Wiki <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a + href="https://wiki.apache.org/incubator/StratosphereProposal"; + target="blank">Incubator proposal <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="http://www.apache.org/licenses/LICENSE-2.0"; + target="blank">License <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="https://github.com/apache/incubator-flink"; + target="blank">Source code <span + class="glyphicon glyphicon-new-window"></span></a></li> + </ul> + </div> + </div> + </div> + <div class="af-footer-bar"> + <div class="container"> + <p>Copyright © 2014-2015, <a href="http://www.apache.org";>The Apache Software Foundation</a>. All Rights Reserved. Apache and the Apache feather logo are trademarks of the Apache Software Foundation. + </p> + <div> + <div style="float:left"> + <p> + <a href="/privacy-policy.html" title="Privacy Policy" class="af-privacy-policy">Privacy Policy</a> + </p> + </div> + <div style="float:right"> + <p> + <a href="/blog/feed.xml" class="af-privacy-policy">RSS Feed</a> + </p> + </div> + </div> + </div> + </div> +</footer> + + <!-- Google Analytics --> + <script> + (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ + (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), + m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) + })(window,document,'script','//www.google-analytics.com/analytics.js','ga'); + + ga('create', 'UA-52545728-1', 'auto'); + ga('send', 'pageview'); + </script> + <script src="/js/main/jquery.mobile.events.min.js"></script> + <script src="/js/main/main.js"></script> + </body> +</html> http://git-wip-us.apache.org/repos/asf/flink-web/blob/a16dddeb/content/news/2014/02/24/stratosphere-google-summer-of-code-2014.html ---------------------------------------------------------------------- diff --git a/content/news/2014/02/24/stratosphere-google-summer-of-code-2014.html b/content/news/2014/02/24/stratosphere-google-summer-of-code-2014.html new file mode 100644 index 0000000..85a9558 --- /dev/null +++ b/content/news/2014/02/24/stratosphere-google-summer-of-code-2014.html @@ -0,0 +1,299 @@ +<!DOCTYPE html> +<html lang="en"> + <head> + <meta charset="utf-8"> + <meta http-equiv="X-UA-Compatible" content="IE=edge"> + <meta name="viewport" content="width=device-width, initial-scale=1"> + + <title>Apache Flink: Stratosphere got accepted for Google Summer of Code 2014</title> + <link rel="shortcut icon" href="favicon.ico" type="image/x-icon"> + <link rel="icon" href="favicon.ico" type="image/x-icon"> + <link rel="stylesheet" href="/css/bootstrap.css"> + <link rel="stylesheet" href="/css/bootstrap-lumen-custom.css"> + <link rel="stylesheet" href="/css/syntax.css"> + <link rel="stylesheet" href="/css/custom.css"> + <link href="/css/main/main.css" rel="stylesheet"> + <link href="/blog/feed.xml" rel="alternate" type="application/rss+xml" title="Flink Blog RSS feed" /> + <!-- <link href="//maxcdn.bootstrapcdn.com/font-awesome/4.1.0/css/font-awesome.min.css" rel="stylesheet"> --> + <script src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.0/jquery.min.js";></script> + <script src="/js/bootstrap.min.js"></script> + <script src="/js/codetabs.js"></script> + </head> + <body> + <div class="af-header-container af-inner-pages-navigation"> + <header> + <div class="container"> + <div class="row"> + <div class="col-md-1 af-mobile-nav-bar"> + <a href="/" title="Home"> + <img class="hidden-xs hidden-sm img-responsive" + src="/img/main/logo.png" alt="Apache Flink Logo"> + </a> + <div class="row visible-xs"> + <div class="col-xs-3"> + <a href="/" title="Home"> + <img class="hidden-x hidden-sm img-responsive" + src="/img/main/logo.png" alt="Apache Flink Logo"> + </a> + </div> + <div class="col-xs-5"></div> + <div class="col-xs-4"> + <div class="af-mobile-btn"> + <span class="glyphicon glyphicon-plus"></span> + </div> + </div> + </div> + </div> + <!-- Navigation --> + <div class="col-md-11"> + <nav class="af-main-nav" role="navigation"> + <ul> + <li><a href="#" class="af-nav-links">Quickstart + <b class="caret"></b> + </a> + <ul class="af-dropdown-menu"> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/setup_quickstart.html";>Setup + Flink</a></li> + <li><a + href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/java_api_quickstart.html";>Java + API</a></li> + <li><a + href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/scala_api_quickstart.html";>Scala + API</a></li> + </ul></li> + <li><a href="/downloads.html">Download</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/faq.html";>FAQ</a></li> + <li><a href="#" class="af-nav-links">Documentation <b + class="caret"></b></a> + <ul class="af-dropdown-menu"> + <li class="af-separator">Current Snapshot:</li> + <li></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-master/";>0.9</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-master/api/java";>0.9 Javadocs</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-master/api/scala/index.html#org.apache.flink.api.scala.package";>0.9 Scaladocs</a></li> + <li class="divider"></li> + <li class="af-separator">Current Stable:</li> + <li></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/";>0.8.1</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/api/java";>0.8.1 Javadocs</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/api/scala/index.html#org.apache.flink.api.scala.package";>0.8.1 Scaladocs</a></li> + <li class="divider"></li> + <li></li> + <li><a href="/archive.html">Archive</a></li> + <li></li> + </ul></li> + <li><a href="#" class="af-nav-links">Community <b + class="caret"></b></a> + <ul class="af-dropdown-menu"> + <li><a href="/community.html#getting-help">Getting Help</a></li> + <li><a href="/community.html#mailing-lists">Mailing Lists</a></li> + <li><a href="/community.html#issues">Issues</a></li> + <li><a href="/community.html#team">Team</a></li> + <li class="divider"></li> + <li><a href="/how-to-contribute.html">How To + Contribute</a></li> + <li><a href="/coding_guidelines.html">Coding + Guidelines</a></li> + </ul></li> + <li><a href="#" class="af-nav-links">Project <b + class="caret"></b></a> + <ul class="af-dropdown-menu"> + <li><a href="/material.html">Material</a></li> + <li><a href="http://www.apache.org/";>Apache Software + Foundation <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a + href="https://cwiki.apache.org/confluence/display/FLINK";>Wiki + <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a + href="https://wiki.apache.org/incubator/StratosphereProposal";>Incubator + Proposal <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a href="http://www.apache.org/licenses/LICENSE-2.0";>License + <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a href="https://github.com/apache/incubator-flink";>Source + Code <span class="glyphicon glyphicon-new-window"></span> + </a></li> + </ul></li> + <li><a href="/blog/index.html" class="">Blog</a></li> + </ul> + </nav> + </div> + </div> + </div> + </header> +</div> + + + <div style="padding-top:50px" class="container"> + <div class="container"> + <div class="row"> + <div class="col-md-2"></div> + <div class="col-md-8"> + <article> + <h2>Stratosphere got accepted for Google Summer of Code 2014</h2> + <p class="meta">24 Feb 2014</p> + <div> + <div class="lead">Students: Apply now for exciting summer projects in the Big Data / Analytics field</div> + +<p>We are pleased to announce that Stratosphere got accepted to <a href="http://www.google-melange.com/gsoc/homepage/google/gsoc2014";>Google Summer of Code 2014</a> as a mentoring organization. This means that we will host a bunch of students to conduct projects within Stratosphere over the summer. <a href="http://en.flossmanuals.net/GSoCStudentGuide/";>Read more on the GSoC manual for students</a> and the <a href="http://www.google-melange.com/gsoc/document/show/gsoc_program/google/gsoc2014/help_page";>official FAQ</a>. Students can improve their coding skills, learn to work with open-source projects, improve their CV and get a nice paycheck from Google.</p> + +<p>If you are an interested student, check out our <a href="https://github.com/stratosphere/stratosphere/wiki/Google-Summer-of-Code-2014";>idea list</a> in the wiki. It contains different projects with varying ranges of difficulty and requirement profiles. Students can also suggest their own projects.</p> + +<p>We welcome students to sign up at our <a href="https://groups.google.com/forum/#!forum/stratosphere-dev";>developer mailing list</a> to discuss their ideas. +Applying students can use our wiki (create a new page) to create a project proposal. We are happy to have a look at it.</p> + + </div> + </article> + </div> + <div class="col-md-2"></div> + </div> + <div class="row" style="padding-top:30px"> + <div class="col-md-2"></div> + <div class="col-md-8"> + <div id="disqus_thread"></div> + <script type="text/javascript"> + /* * * CONFIGURATION VARIABLES: EDIT BEFORE PASTING INTO YOUR WEBPAGE * * */ + var disqus_shortname = 'stratosphere-eu'; // required: replace example with your forum shortname + + /* * * DON'T EDIT BELOW THIS LINE * * */ + (function() { + var dsq = document.createElement('script'); dsq.type = 'text/javascript'; dsq.async = true; + dsq.src = '//' + disqus_shortname + '.disqus.com/embed.js'; + (document.getElementsByTagName('head')[0] || document.getElementsByTagName('body')[0]).appendChild(dsq); + })(); + </script> + <noscript>Please enable JavaScript to view the <a href="http://disqus.com/?ref_noscript";>comments powered by Disqus.</a></noscript> + <a href="http://disqus.com"; class="dsq-brlink">comments powered by <span class="logo-disqus">Disqus</span></a> + </div> + <div class="col-md-2"></div> + </div> +</div> + + </div> + <!--<section id="af-upfooter" class="af-section"> + <div class="container"> + <p>Apache Flink is an effort undergoing incubation at The Apache + Software Foundation (ASF), sponsored by the Apache Incubator PMC. + Incubation is required of all newly accepted projects until a further + review indicates that the infrastructure, communications, and + decision making process have stabilized in a manner consistent with + other successful ASF projects. While incubation status is not + necessarily a reflection of the completeness or stability of the + code, it does indicate that the project has yet to be fully endorsed + by the ASF.</p> + <a href="http://incubator.apache.org";> <img class="img-responsive" + src="/img/main/apache-incubator-logo.png" alt="Apache Flink" /> + </a> + <p class="text-center"> + <a href="/privacy-policy.html" title="Privacy Policy" + class="af-privacy-policy">Privacy Policy</a> + </p> + </div> +</section>--> + +<footer id="af-footer"> + <div class="container"> + <div class="row"> + <div class="col-md-3"> + <h3>Documentation</h3> + <ul class="af-footer-menu"> + + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/";>0.8.1</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/api/java/";>0.8.1 Javadocs</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/api/scala/index.html#org.apache.flink.api.scala.package";>0.8.1 Scaladocs</a></li> + </ul> + </div> + <div class="col-md-3"> + <h3>Community</h3> + <ul class="af-footer-menu"> + <li><a href="/community.html#mailing-lists">Mailing Lists</a></li> + <li><a href="https://issues.apache.org/jira/browse/FLINK"; + target="blank">Issues <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="/community.html#team">Team</a></li> + <li><a href="/how-to-contribute.html">How to contribute</a></li> + <li><a href="/coding_guidelines.html">Coding Guidelines</a></li> + </ul> + </div> + <div class="col-md-3"> + <h3>ASF</h3> + <ul class="af-footer-menu"> + <li><a href="http://www.apache.org/"; target="blank">Apache + Software foundation <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a + href="http://www.apache.org/foundation/how-it-works.html"; + target="blank">How it works <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="http://www.apache.org/foundation/thanks.html"; + target="blank">Thanks <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a + href="http://www.apache.org/foundation/sponsorship.html"; + target="blank">Become a sponsor <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="http://incubator.apache.org/projects/flink.html"; + target="blank">Incubation status page <span + class="glyphicon glyphicon-new-window"></span></a></li> + </ul> + </div> + <div class="col-md-3"> + <h3>Project</h3> + <ul class="af-footer-menu"> + <li><a href="/material.html" target="blank">Material <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a + href="https://cwiki.apache.org/confluence/display/FLINK"; + target="blank">Wiki <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a + href="https://wiki.apache.org/incubator/StratosphereProposal"; + target="blank">Incubator proposal <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="http://www.apache.org/licenses/LICENSE-2.0"; + target="blank">License <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="https://github.com/apache/incubator-flink"; + target="blank">Source code <span + class="glyphicon glyphicon-new-window"></span></a></li> + </ul> + </div> + </div> + </div> + <div class="af-footer-bar"> + <div class="container"> + <p>Copyright © 2014-2015, <a href="http://www.apache.org";>The Apache Software Foundation</a>. All Rights Reserved. Apache and the Apache feather logo are trademarks of the Apache Software Foundation. + </p> + <div> + <div style="float:left"> + <p> + <a href="/privacy-policy.html" title="Privacy Policy" class="af-privacy-policy">Privacy Policy</a> + </p> + </div> + <div style="float:right"> + <p> + <a href="/blog/feed.xml" class="af-privacy-policy">RSS Feed</a> + </p> + </div> + </div> + </div> + </div> +</footer> + + <!-- Google Analytics --> + <script> + (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ + (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), + m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) + })(window,document,'script','//www.google-analytics.com/analytics.js','ga'); + + ga('create', 'UA-52545728-1', 'auto'); + ga('send', 'pageview'); + </script> + <script src="/js/main/jquery.mobile.events.min.js"></script> + <script src="/js/main/main.js"></script> + </body> +</html> http://git-wip-us.apache.org/repos/asf/flink-web/blob/a16dddeb/content/news/2014/04/16/stratosphere-goes-apache-incubator.html ---------------------------------------------------------------------- diff --git a/content/news/2014/04/16/stratosphere-goes-apache-incubator.html b/content/news/2014/04/16/stratosphere-goes-apache-incubator.html new file mode 100644 index 0000000..7345c5a --- /dev/null +++ b/content/news/2014/04/16/stratosphere-goes-apache-incubator.html @@ -0,0 +1,294 @@ +<!DOCTYPE html> +<html lang="en"> + <head> + <meta charset="utf-8"> + <meta http-equiv="X-UA-Compatible" content="IE=edge"> + <meta name="viewport" content="width=device-width, initial-scale=1"> + + <title>Apache Flink: Stratosphere accepted as Apache Incubator Project</title> + <link rel="shortcut icon" href="favicon.ico" type="image/x-icon"> + <link rel="icon" href="favicon.ico" type="image/x-icon"> + <link rel="stylesheet" href="/css/bootstrap.css"> + <link rel="stylesheet" href="/css/bootstrap-lumen-custom.css"> + <link rel="stylesheet" href="/css/syntax.css"> + <link rel="stylesheet" href="/css/custom.css"> + <link href="/css/main/main.css" rel="stylesheet"> + <link href="/blog/feed.xml" rel="alternate" type="application/rss+xml" title="Flink Blog RSS feed" /> + <!-- <link href="//maxcdn.bootstrapcdn.com/font-awesome/4.1.0/css/font-awesome.min.css" rel="stylesheet"> --> + <script src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.0/jquery.min.js";></script> + <script src="/js/bootstrap.min.js"></script> + <script src="/js/codetabs.js"></script> + </head> + <body> + <div class="af-header-container af-inner-pages-navigation"> + <header> + <div class="container"> + <div class="row"> + <div class="col-md-1 af-mobile-nav-bar"> + <a href="/" title="Home"> + <img class="hidden-xs hidden-sm img-responsive" + src="/img/main/logo.png" alt="Apache Flink Logo"> + </a> + <div class="row visible-xs"> + <div class="col-xs-3"> + <a href="/" title="Home"> + <img class="hidden-x hidden-sm img-responsive" + src="/img/main/logo.png" alt="Apache Flink Logo"> + </a> + </div> + <div class="col-xs-5"></div> + <div class="col-xs-4"> + <div class="af-mobile-btn"> + <span class="glyphicon glyphicon-plus"></span> + </div> + </div> + </div> + </div> + <!-- Navigation --> + <div class="col-md-11"> + <nav class="af-main-nav" role="navigation"> + <ul> + <li><a href="#" class="af-nav-links">Quickstart + <b class="caret"></b> + </a> + <ul class="af-dropdown-menu"> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/setup_quickstart.html";>Setup + Flink</a></li> + <li><a + href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/java_api_quickstart.html";>Java + API</a></li> + <li><a + href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/scala_api_quickstart.html";>Scala + API</a></li> + </ul></li> + <li><a href="/downloads.html">Download</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/faq.html";>FAQ</a></li> + <li><a href="#" class="af-nav-links">Documentation <b + class="caret"></b></a> + <ul class="af-dropdown-menu"> + <li class="af-separator">Current Snapshot:</li> + <li></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-master/";>0.9</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-master/api/java";>0.9 Javadocs</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-master/api/scala/index.html#org.apache.flink.api.scala.package";>0.9 Scaladocs</a></li> + <li class="divider"></li> + <li class="af-separator">Current Stable:</li> + <li></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/";>0.8.1</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/api/java";>0.8.1 Javadocs</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/api/scala/index.html#org.apache.flink.api.scala.package";>0.8.1 Scaladocs</a></li> + <li class="divider"></li> + <li></li> + <li><a href="/archive.html">Archive</a></li> + <li></li> + </ul></li> + <li><a href="#" class="af-nav-links">Community <b + class="caret"></b></a> + <ul class="af-dropdown-menu"> + <li><a href="/community.html#getting-help">Getting Help</a></li> + <li><a href="/community.html#mailing-lists">Mailing Lists</a></li> + <li><a href="/community.html#issues">Issues</a></li> + <li><a href="/community.html#team">Team</a></li> + <li class="divider"></li> + <li><a href="/how-to-contribute.html">How To + Contribute</a></li> + <li><a href="/coding_guidelines.html">Coding + Guidelines</a></li> + </ul></li> + <li><a href="#" class="af-nav-links">Project <b + class="caret"></b></a> + <ul class="af-dropdown-menu"> + <li><a href="/material.html">Material</a></li> + <li><a href="http://www.apache.org/";>Apache Software + Foundation <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a + href="https://cwiki.apache.org/confluence/display/FLINK";>Wiki + <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a + href="https://wiki.apache.org/incubator/StratosphereProposal";>Incubator + Proposal <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a href="http://www.apache.org/licenses/LICENSE-2.0";>License + <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a href="https://github.com/apache/incubator-flink";>Source + Code <span class="glyphicon glyphicon-new-window"></span> + </a></li> + </ul></li> + <li><a href="/blog/index.html" class="">Blog</a></li> + </ul> + </nav> + </div> + </div> + </div> + </header> +</div> + + + <div style="padding-top:50px" class="container"> + <div class="container"> + <div class="row"> + <div class="col-md-2"></div> + <div class="col-md-8"> + <article> + <h2>Stratosphere accepted as Apache Incubator Project</h2> + <p class="meta">16 Apr 2014</p> + <div> + <p>We are happy to announce that Stratosphere has been accepted as a project for the <a href="https://incubator.apache.org/";>Apache Incubator</a>. The <a href="https://wiki.apache.org/incubator/StratosphereProposal";>proposal</a> has been accepted by the Incubator PMC members earlier this week. The Apache Incubator is the first step in the process of giving a project to the <a href="http://apache.org";>Apache Software Foundation</a>. While under incubation, the project will move to the Apache infrastructure and adopt the community-driven development principles of the Apache Foundation. Projects can graduate from incubation to become top-level projects if they show activity, a healthy community dynamic, and releases.</p> + +<p>We are glad to have Alan Gates as champion on board, as well as a set of great mentors, including Sean Owen, Ted Dunning, Owen O'Malley, Henry Saputra, and Ashutosh Chauhan. We are confident that we will make this a great open source effort.</p> + + </div> + </article> + </div> + <div class="col-md-2"></div> + </div> + <div class="row" style="padding-top:30px"> + <div class="col-md-2"></div> + <div class="col-md-8"> + <div id="disqus_thread"></div> + <script type="text/javascript"> + /* * * CONFIGURATION VARIABLES: EDIT BEFORE PASTING INTO YOUR WEBPAGE * * */ + var disqus_shortname = 'stratosphere-eu'; // required: replace example with your forum shortname + + /* * * DON'T EDIT BELOW THIS LINE * * */ + (function() { + var dsq = document.createElement('script'); dsq.type = 'text/javascript'; dsq.async = true; + dsq.src = '//' + disqus_shortname + '.disqus.com/embed.js'; + (document.getElementsByTagName('head')[0] || document.getElementsByTagName('body')[0]).appendChild(dsq); + })(); + </script> + <noscript>Please enable JavaScript to view the <a href="http://disqus.com/?ref_noscript";>comments powered by Disqus.</a></noscript> + <a href="http://disqus.com"; class="dsq-brlink">comments powered by <span class="logo-disqus">Disqus</span></a> + </div> + <div class="col-md-2"></div> + </div> +</div> + + </div> + <!--<section id="af-upfooter" class="af-section"> + <div class="container"> + <p>Apache Flink is an effort undergoing incubation at The Apache + Software Foundation (ASF), sponsored by the Apache Incubator PMC. + Incubation is required of all newly accepted projects until a further + review indicates that the infrastructure, communications, and + decision making process have stabilized in a manner consistent with + other successful ASF projects. While incubation status is not + necessarily a reflection of the completeness or stability of the + code, it does indicate that the project has yet to be fully endorsed + by the ASF.</p> + <a href="http://incubator.apache.org";> <img class="img-responsive" + src="/img/main/apache-incubator-logo.png" alt="Apache Flink" /> + </a> + <p class="text-center"> + <a href="/privacy-policy.html" title="Privacy Policy" + class="af-privacy-policy">Privacy Policy</a> + </p> + </div> +</section>--> + +<footer id="af-footer"> + <div class="container"> + <div class="row"> + <div class="col-md-3"> + <h3>Documentation</h3> + <ul class="af-footer-menu"> + + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/";>0.8.1</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/api/java/";>0.8.1 Javadocs</a></li> + <li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.8/api/scala/index.html#org.apache.flink.api.scala.package";>0.8.1 Scaladocs</a></li> + </ul> + </div> + <div class="col-md-3"> + <h3>Community</h3> + <ul class="af-footer-menu"> + <li><a href="/community.html#mailing-lists">Mailing Lists</a></li> + <li><a href="https://issues.apache.org/jira/browse/FLINK"; + target="blank">Issues <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="/community.html#team">Team</a></li> + <li><a href="/how-to-contribute.html">How to contribute</a></li> + <li><a href="/coding_guidelines.html">Coding Guidelines</a></li> + </ul> + </div> + <div class="col-md-3"> + <h3>ASF</h3> + <ul class="af-footer-menu"> + <li><a href="http://www.apache.org/"; target="blank">Apache + Software foundation <span class="glyphicon glyphicon-new-window"></span> + </a></li> + <li><a + href="http://www.apache.org/foundation/how-it-works.html"; + target="blank">How it works <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="http://www.apache.org/foundation/thanks.html"; + target="blank">Thanks <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a + href="http://www.apache.org/foundation/sponsorship.html"; + target="blank">Become a sponsor <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="http://incubator.apache.org/projects/flink.html"; + target="blank">Incubation status page <span + class="glyphicon glyphicon-new-window"></span></a></li> + </ul> + </div> + <div class="col-md-3"> + <h3>Project</h3> + <ul class="af-footer-menu"> + <li><a href="/material.html" target="blank">Material <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a + href="https://cwiki.apache.org/confluence/display/FLINK"; + target="blank">Wiki <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a + href="https://wiki.apache.org/incubator/StratosphereProposal"; + target="blank">Incubator proposal <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="http://www.apache.org/licenses/LICENSE-2.0"; + target="blank">License <span + class="glyphicon glyphicon-new-window"></span></a></li> + <li><a href="https://github.com/apache/incubator-flink"; + target="blank">Source code <span + class="glyphicon glyphicon-new-window"></span></a></li> + </ul> + </div> + </div> + </div> + <div class="af-footer-bar"> + <div class="container"> + <p>Copyright © 2014-2015, <a href="http://www.apache.org";>The Apache Software Foundation</a>. All Rights Reserved. Apache and the Apache feather logo are trademarks of the Apache Software Foundation. + </p> + <div> + <div style="float:left"> + <p> + <a href="/privacy-policy.html" title="Privacy Policy" class="af-privacy-policy">Privacy Policy</a> + </p> + </div> + <div style="float:right"> + <p> + <a href="/blog/feed.xml" class="af-privacy-policy">RSS Feed</a> + </p> + </div> + </div> + </div> + </div> +</footer> + + <!-- Google Analytics --> + <script> + (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ + (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), + m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) + })(window,document,'script','//www.google-analytics.com/analytics.js','ga'); + + ga('create', 'UA-52545728-1', 'auto'); + ga('send', 'pageview'); + </script> + <script src="/js/main/jquery.mobile.events.min.js"></script> + <script src="/js/main/main.js"></script> + </body> +</html>
