blob: fbecfe7d5d446fe665524657a9b7fcf6599d9907 [file] [log] [blame]
<!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">
<!-- The above 3 meta tags *must* come first in the head; any other head content must come *after* these tags -->
<title>Apache Flink: Blog</title>
<link rel="shortcut icon" href="/favicon.ico" type="image/x-icon">
<link rel="icon" href="/favicon.ico" type="image/x-icon">
<!-- Bootstrap -->
<link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/css/bootstrap.min.css">
<link rel="stylesheet" href="/css/flink.css">
<link rel="stylesheet" href="/css/syntax.css">
<!-- Blog RSS feed -->
<link href="/blog/feed.xml" rel="alternate" type="application/rss+xml" title="Apache Flink Blog: RSS feed" />
<!-- HTML5 shim and Respond.js for IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
<!--[if lt IE 9]>
<script src="https://oss.maxcdn.com/html5shiv/3.7.2/html5shiv.min.js"></script>
<script src="https://oss.maxcdn.com/respond/1.4.2/respond.min.js"></script>
<![endif]-->
</head>
<body>
<!-- Top navbar. -->
<nav class="navbar navbar-default navbar-fixed-top">
<div class="container">
<!-- The logo. -->
<div class="navbar-header">
<button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#bs-example-navbar-collapse-1">
<span class="icon-bar"></span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
</button>
<div class="navbar-logo">
<a href="/"><img alt="Apache Flink" src="/img/navbar-brand-logo.jpg" width="78px" height="40px"></a>
</div>
</div><!-- /.navbar-header -->
<!-- The navigation links. -->
<div class="collapse navbar-collapse" id="bs-example-navbar-collapse-1">
<ul class="nav navbar-nav">
<!-- Overview -->
<li><a href="/index.html">Overview</a></li>
<!-- Quickstart -->
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-expanded="false">Quickstart <span class="caret"></span></a>
<ul class="dropdown-menu" role="menu">
<li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.9/quickstart/setup_quickstart.html">Setup</a></li>
<li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.9/quickstart/java_api_quickstart.html">Java API</a></li>
<li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.9/quickstart/scala_api_quickstart.html">Scala API</a></li>
<li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.9/quickstart/run_example_quickstart.html">Run Step-by-Step Example</a></li>
</ul>
</li>
<!-- Features -->
<li><a href="/features.html">Features</a></li>
<!-- Downloads -->
<li><a href="/downloads.html">Downloads</a></li>
<!-- Documentation -->
<li class="dropdown">
<a href="" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-expanded="false">Documentation <span class="caret"></span></a>
<ul class="dropdown-menu" role="menu">
<!-- Latest stable release -->
<li role="presentation" class="dropdown-header"><strong>Latest Release</strong> (Stable)</li>
<li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.9">0.9.0 Documentation</a></li>
<li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.9/api/java" class="active">0.9.0 Javadocs</a></li>
<li><a href="http://ci.apache.org/projects/flink/flink-docs-release-0.9/api/scala/index.html" class="active">0.9.0 ScalaDocs</a></li>
<!-- Snapshot docs -->
<li class="divider"></li>
<li role="presentation" class="dropdown-header"><strong>Snapshot</strong> (Development)</li>
<li><a href="http://ci.apache.org/projects/flink/flink-docs-master">0.10 Documentation</a></li>
<li><a href="http://ci.apache.org/projects/flink/flink-docs-master/api/java" class="active">0.10 Javadocs</a></li>
<li><a href="http://ci.apache.org/projects/flink/flink-docs-master/api/scala/index.html" class="active">0.10 ScalaDocs</a></li>
<!-- Wiki -->
<li class="divider"></li>
<li><a href="https://cwiki.apache.org/confluence/display/FLINK/Apache+Flink+Home"><small><span class="glyphicon glyphicon-new-window"></span></small> Wiki</a></li>
</ul>
</li>
<!-- FAQ -->
<li><a href="/faq.html">FAQ</a></li>
</ul>
<ul class="nav navbar-nav navbar-right">
<!-- Blog -->
<li class=" active hidden-md hidden-sm"><a href="/blog/">Blog</a></li>
<li class="dropdown hidden-md hidden-sm">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-expanded="false">Community <span class="caret"></span></a>
<ul class="dropdown-menu" role="menu">
<!-- Community -->
<li role="presentation" class="dropdown-header"><strong>Community</strong></li>
<li><a href="/community.html#mailing-lists">Mailing Lists</a></li>
<li><a href="/community.html#irc">IRC</a></li>
<li><a href="/community.html#stack-overflow">Stack Overflow</a></li>
<li><a href="/community.html#issue-tracker">Issue Tracker</a></li>
<li><a href="/community.html#source-code">Source Code</a></li>
<li><a href="/community.html#people">People</a></li>
<!-- Contribute -->
<li class="divider"></li>
<li role="presentation" class="dropdown-header"><strong>Contribute</strong></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 class="dropdown hidden-md hidden-sm">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-expanded="false">Project <span class="caret"></span></a>
<ul class="dropdown-menu" role="menu">
<!-- Project -->
<li role="presentation" class="dropdown-header"><strong>Project</strong></li>
<li><a href="/material.html">Material</a></li>
<li><a href="https://twitter.com/apacheflink"><small><span class="glyphicon glyphicon-new-window"></span></small> Twitter</a></li>
<li><a href="https://github.com/apache/flink"><small><span class="glyphicon glyphicon-new-window"></span></small> GitHub</a></li>
<li><a href="https://cwiki.apache.org/confluence/display/FLINK/Apache+Flink+Home"><small><span class="glyphicon glyphicon-new-window"></span></small> Wiki</a></li>
</ul>
</li>
</ul>
</div><!-- /.navbar-collapse -->
</div><!-- /.container -->
</nav>
<!-- Main content. -->
<div class="container">
<div class="row">
<div class="col-sm-12"><h1>Blog</h1></div>
</div>
<div class="row">
<div class="col-sm-8">
<!-- Blog posts -->
<article>
<h2 class="blog-title"><a href="/news/2014/01/28/querying_mongodb.html">Accessing Data Stored in MongoDB with Stratosphere</a></h2>
<p>28 Jan 2014 by Robert Metzger (<a href="https://twitter.com/rmetzger_">@rmetzger_</a>)</p>
<p><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>
</p>
<p><a href="/news/2014/01/28/querying_mongodb.html">Continue reading &raquo;</a></p>
</article>
<hr>
<article>
<h2 class="blog-title"><a href="/news/2014/01/26/optimizer_plan_visualization_tool.html">Optimizer Plan Visualization Tool</a></h2>
<p>26 Jan 2014</p>
<p><p>Stratosphere’s hybrid approach combines <strong>MapReduce</strong> and <strong>MPP database</strong> techniques. One central part of this approach is to have a <strong>separation between the programming (API) and the way programs are executed</strong> <em>(execution plans)</em>. The <strong>compiler/optimizer</strong> decides the details concerning caching or when to partition/broadcast with a holistic view of the program. The same program may actually be executed differently in different scenarios (input data of different sizes, different number of machines).</p>
</p>
<p><a href="/news/2014/01/26/optimizer_plan_visualization_tool.html">Continue reading &raquo;</a></p>
</article>
<hr>
<article>
<h2 class="blog-title"><a href="/news/2014/01/13/stratosphere-release-0.4.html">Stratosphere 0.4 Released</a></h2>
<p>13 Jan 2014</p>
<p><p>We are pleased to announce that version 0.4 of the Stratosphere system has been released.</p>
</p>
<p><a href="/news/2014/01/13/stratosphere-release-0.4.html">Continue reading &raquo;</a></p>
</article>
<hr>
<article>
<h2 class="blog-title"><a href="/news/2014/01/12/0.4-migration-guide.html">Stratosphere Version 0.4 Migration Guide</a></h2>
<p>12 Jan 2014</p>
<p><p>This guide is intended to help users of previous Stratosphere versions to migrate their programs to the new API of v0.4.</p>
</p>
<p><a href="/news/2014/01/12/0.4-migration-guide.html">Continue reading &raquo;</a></p>
</article>
<hr>
<article>
<h2 class="blog-title"><a href="/news/2014/01/10/stratosphere-hadoop-summit.html">Stratosphere got accepted to the Hadoop Summit Europe in Amsterdam</a></h2>
<p>10 Jan 2014</p>
<p><p>The Stratosphere team is proud to announce that it is going to present at the <a href="http://hadoopsummit.org/amsterdam/">Hadoop Summit 2014 in Amsterdam</a> on April 2-3. Our talk “Big Data looks tiny from Stratosphere” is part of the “Future of Hadoop” Track. The talk abstract already made it into the top 5 in the <a href="https://hadoopsummit.uservoice.com/forums/196822-future-of-apache-hadoop/filters/top">Community Vote</a> that took place by the end of last year.</p>
</p>
<p><a href="/news/2014/01/10/stratosphere-hadoop-summit.html">Continue reading &raquo;</a></p>
</article>
<hr>
<article>
<h2 class="blog-title"><a href="/news/2013/12/13/humboldt-innovation-award.html">Stratosphere wins award at Humboldt Innovation Competition "Big Data: Research meets Startups"</a></h2>
<p>13 Dec 2013</p>
<p> <p> Stratosphere won the second place in
the <a href="http://www.humboldt-innovation.de/de/newsdetail/News/View/Forum%2BJunge%2BSpitzenforscher%2BBIG%2BData%2B%2BResearch%2Bmeets%2BStartups-123.html">competition</a>
organized by Humboldt Innovation on "Big Data: Research meets
Startups," where several research projects were evaluated by a
panel of experts from the Berlin startup ecosystem. The award
includes a monetary prize of 10,000 euros.
</p>
</p>
<p><a href="/news/2013/12/13/humboldt-innovation-award.html">Continue reading &raquo;</a></p>
</article>
<hr>
<article>
<h2 class="blog-title"><a href="/news/2013/10/21/cikm2013-paper.html">Paper "All Roads Lead to Rome: Optimistic Recovery for Distributed Iterative Data Processing" accepted at CIKM 2013</a></h2>
<p>21 Oct 2013</p>
<p><p>Our paper ““All Roads Lead to Rome:” Optimistic Recovery for Distributed
Iterative Data Processing” authored by Sebastian Schelter, Kostas
Tzoumas, Stephan Ewen and Volker Markl has been accepted accepted at the
ACM International Conference on Information and Knowledge Management
(CIKM 2013) in San Francisco.</p>
</p>
<p><a href="/news/2013/10/21/cikm2013-paper.html">Continue reading &raquo;</a></p>
</article>
<hr>
<article>
<h2 class="blog-title"><a href="/news/2013/03/27/www-demo-paper.html">Demo Paper "Large-Scale Social-Media Analytics on Stratosphere" Accepted at WWW 2013</a></h2>
<p>27 Mar 2013</p>
<p> <p>Our demo submission<br />
<strong><cite>"Large-Scale Social-Media Analytics on Stratosphere"</cite></strong><br />
by Christoph Boden, Marcel Karnstedt, Miriam Fernandez and Volker Markl<br />
has been accepted for WWW 2013 in Rio de Janeiro, Brazil.</p>
<p>Visit our demo, and talk to us if you are attending WWW 2013.</p>
<p><strong>Abstract:</strong><br />
The importance of social-media platforms and online communities - in business as well as public context - is more and more acknowledged and appreciated by industry and researchers alike. Consequently, a wide range of analytics has been proposed to understand, steer, and exploit the mechanics and laws driving their functionality and creating the resulting benefits. However, analysts usually face significant problems in scaling existing and novel approaches to match the data volume and size of modern online communities. In this work, we propose and demonstrate the usage of the massively parallel data prossesing system Stratosphere, based on second order functions as an extended notion of the MapReduce paradigm, to provide a new level of scalability to such social-media analytics. Based on the popular example of role analysis, we present and illustrate how this massively parallel approach can be leveraged to scale out complex data-mining tasks, while providing a programming approach that eases the formulation of complete analytical workflows.</p>
</p>
<p><a href="/news/2013/03/27/www-demo-paper.html">Continue reading &raquo;</a></p>
</article>
<hr>
<article>
<h2 class="blog-title"><a href="/news/2012/11/21/previewICDE2013.html">ICDE 2013 Demo Preview</a></h2>
<p>21 Nov 2012</p>
<p> <p>This is a preview of our demo that will be presented at ICDE 2013 in Brisbane.<br />
The demo shows how static code analysis can be leveraged to reordered UDF operators in data flow programs.</p>
<p>Detailed information can be found in our papers which are available on the <a href="/publications">publication</a> page.</p>
<p><iframe width="420" height="315" src="http://www.youtube.com/embed/ZYwCMgPXFVE" frameborder="0" allowfullscreen></iframe></p>
</p>
<p><a href="/news/2012/11/21/previewICDE2013.html">Continue reading &raquo;</a></p>
</article>
<hr>
<article>
<h2 class="blog-title"><a href="/news/2012/11/12/btw2013demo.html">Stratosphere Demo Paper Accepted for BTW 2013</a></h2>
<p>12 Nov 2012</p>
<p> <p>Our demo submission<br />
<strong><cite>"Applying Stratosphere for Big Data Analytics"</cite></strong><br />
has been accepted for BTW 2013 in Magdeburg, Germany.<br />
The demo focuses on Stratosphere's query language Meteor, which has been presented in our paper <cite>"Meteor/Sopremo: An Extensible Query Language and Operator Model"</cite> <a href="/assets/papers/Sopremo_Meteor BigData.pdf">[pdf]</a> at the BigData workshop associated with VLDB 2012 in Istanbul.</p>
<p>Visit our demo, and talk to us if you are going to attend BTW 2013.</p>
<p><strong>Abstract:</strong><br />
Analyzing big data sets as they occur in modern business and science applications requires query languages that allow for the specification of complex data processing tasks. Moreover, these ideally declarative query specifications have to be optimized, parallelized and scheduled for processing on massively parallel data processing platforms. This paper demonstrates the application of Stratosphere to different kinds of Big Data Analytics tasks. Using examples from different application domains, we show how to formulate analytical tasks as Meteor queries and execute them with Stratosphere. These examples include data cleansing and information extraction tasks, and a correlation analysis of microblogging and stock trade volume data that we describe in detail in this paper.</p>
</p>
<p><a href="/news/2012/11/12/btw2013demo.html">Continue reading &raquo;</a></p>
</article>
<hr>
<!-- Pagination links -->
<ul class="pager">
<li>
<a href="/blog/page2" class="previous">Previous</a>
</li>
<li>
<span class="page_number ">Page: 3 of 4</span>
</li>
<li>
<a href="/blog/page4" class="next">Next</a>
</li>
</ul>
</div>
<div class="col-sm-4" markdown="1">
<!-- Blog posts by YEAR -->
<h2>2015</h2>
<ul id="markdown-toc">
<li><a href="/news/2015/06/24/announcing-apache-flink-0.9.0-release.html">Announcing Apache Flink 0.9.0</a></li>
<li><a href="/news/2015/05/14/Community-update-April.html">April 2015 in the Flink community</a></li>
<li><a href="/news/2015/05/11/Juggling-with-Bits-and-Bytes.html">Juggling with Bits and Bytes</a></li>
<li><a href="/news/2015/04/13/release-0.9.0-milestone1.html">Announcing Flink 0.9.0-milestone1 preview release</a></li>
<li><a href="/news/2015/04/07/march-in-flink.html">March 2015 in the Flink community</a></li>
<li><a href="/news/2015/03/13/peeking-into-Apache-Flinks-Engine-Room.html">Peeking into Apache Flink's Engine Room</a></li>
<li><a href="/news/2015/03/02/february-2015-in-flink.html">February 2015 in the Flink community</a></li>
<li><a href="/news/2015/02/09/streaming-example.html">Introducing Flink Streaming</a></li>
<li><a href="/news/2015/02/04/january-in-flink.html">January 2015 in the Flink community</a></li>
<li><a href="/news/2015/01/21/release-0.8.html">Apache Flink 0.8.0 available</a></li>
<li><a href="/news/2015/01/06/december-in-flink.html">December 2014 in the Flink community</a></li>
</ul>
<hr>
<h2>2014</h2>
<ul id="markdown-toc">
<li><a href="/news/2014/11/18/hadoop-compatibility.html">Hadoop Compatibility in Flink</a></li>
<li><a href="/news/2014/11/04/release-0.7.0.html">Apache Flink 0.7.0 available</a></li>
<li><a href="/news/2014/10/03/upcoming_events.html">Upcoming Events</a></li>
<li><a href="/news/2014/09/26/release-0.6.1.html">Apache Flink 0.6.1 available</a></li>
<li><a href="/news/2014/08/26/release-0.6.html">Apache Flink 0.6 available</a></li>
<li><a href="/news/2014/05/31/release-0.5.html">Stratosphere version 0.5 available</a></li>
<li><a href="/news/2014/04/16/stratosphere-goes-apache-incubator.html">Stratosphere accepted as Apache Incubator Project</a></li>
<li><a href="/news/2014/02/24/stratosphere-google-summer-of-code-2014.html">Stratosphere got accepted for Google Summer of Code 2014</a></li>
<li><a href="/news/2014/02/18/amazon-elastic-mapreduce-cloud-yarn.html">Use Stratosphere with Amazon Elastic MapReduce</a></li>
<li><a href="/news/2014/01/28/querying_mongodb.html">Accessing Data Stored in MongoDB with Stratosphere</a></li>
<li><a href="/news/2014/01/26/optimizer_plan_visualization_tool.html">Optimizer Plan Visualization Tool</a></li>
<li><a href="/news/2014/01/13/stratosphere-release-0.4.html">Stratosphere 0.4 Released</a></li>
<li><a href="/news/2014/01/12/0.4-migration-guide.html">Stratosphere Version 0.4 Migration Guide</a></li>
<li><a href="/news/2014/01/10/stratosphere-hadoop-summit.html">Stratosphere got accepted to the Hadoop Summit Europe in Amsterdam</a></li>
</ul>
<hr>
<h2>2013</h2>
<ul id="markdown-toc">
<li><a href="/news/2013/12/13/humboldt-innovation-award.html">Stratosphere wins award at Humboldt Innovation Competition "Big Data: Research meets Startups"</a></li>
<li><a href="/news/2013/10/21/cikm2013-paper.html">Paper "All Roads Lead to Rome: Optimistic Recovery for Distributed Iterative Data Processing" accepted at CIKM 2013</a></li>
<li><a href="/news/2013/03/27/www-demo-paper.html">Demo Paper "Large-Scale Social-Media Analytics on Stratosphere" Accepted at WWW 2013</a></li>
</ul>
<hr>
<h2>2012</h2>
<ul id="markdown-toc">
<li><a href="/news/2012/11/21/previewICDE2013.html">ICDE 2013 Demo Preview</a></li>
<li><a href="/news/2012/11/12/btw2013demo.html">Stratosphere Demo Paper Accepted for BTW 2013</a></li>
<li><a href="/news/2012/10/15/icde2013.html">Stratosphere Demo Accepted for ICDE 2013</a></li>
<li><a href="/news/2012/08/21/release02.html">Version 0.2 Released</a></li>
</ul>
</div>
</div>
<hr />
<div class="footer text-center">
<p>Copyright © 2014-2015 <a href="http://apache.org">The Apache Software Foundation</a>. All Rights Reserved.</p>
<p>Apache Flink, Apache, and the Apache feather logo are trademarks of The Apache Software Foundation.</p>
<p><a href="/privacy-policy.html">Privacy Policy</a> &middot; <a href="/blog/feed.xml">RSS feed</a></p>
</div>
</div><!-- /.container -->
<!-- jQuery (necessary for Bootstrap's JavaScript plugins) -->
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.2/jquery.min.js"></script>
<!-- Include all compiled plugins (below), or include individual files as needed -->
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="/js/codetabs.js"></script>
<!-- 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>
</body>
</html>