http://git-wip-us.apache.org/repos/asf/storm-site/blob/ff14ea94/content/releases/0.10.1/documentation/Project-ideas.html ---------------------------------------------------------------------- diff --git a/content/releases/0.10.1/documentation/Project-ideas.html b/content/releases/0.10.1/documentation/Project-ideas.html deleted file mode 100644 index b29ec3d..0000000 --- a/content/releases/0.10.1/documentation/Project-ideas.html +++ /dev/null @@ -1,255 +0,0 @@ -<!DOCTYPE html> -<html> - <head> - <meta charset="utf-8"> - <meta http-equiv="X-UA-Compatible" content="IE=edge"> - <meta name="viewport" content="width=device-width, initial-scale=1"> - - <link rel="shortcut icon" href="/favicon.ico" type="image/x-icon"> - <link rel="icon" href="/favicon.ico" type="image/x-icon"> - - <title>Apache Storm</title> - - <!-- Bootstrap core CSS --> - <link href="/assets/css/bootstrap.min.css" rel="stylesheet"> - <!-- Bootstrap theme --> - <link href="/assets/css/bootstrap-theme.min.css" rel="stylesheet"> - - <!-- Custom styles for this template --> - <link rel="stylesheet" href="http://fortawesome.github.io/Font-Awesome/assets/font-awesome/css/font-awesome.css";> - <link href="/css/style.css" rel="stylesheet"> - <link href="/assets/css/owl.theme.css" rel="stylesheet"> - <link href="/assets/css/owl.carousel.css" rel="stylesheet"> - <script type="text/javascript" src="/assets/js/jquery.min.js"></script> - <script type="text/javascript" src="/assets/js/bootstrap.min.js"></script> - <script type="text/javascript" src="/assets/js/owl.carousel.min.js"></script> - <script type="text/javascript" src="/assets/js/storm.js"></script> - <!-- Just for debugging purposes. Don't actually copy these 2 lines! --> - <!--[if lt IE 9]><script src="../../assets/js/ie8-responsive-file-warning.js"></script><![endif]--> - - <!-- HTML5 shim and Respond.js for IE8 support of HTML5 elements and media queries --> - <!--[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> - <header> - <div class="container-fluid"> - <div class="row"> - <div class="col-md-5"> - <a href="/index.html"><img src="/images/logo.png" class="logo" /></a> - </div> - <div class="col-md-5"> - - <h1>Version: 0.10.1</h1> - - </div> - <div class="col-md-2"> - <a href="/downloads.html" class="btn-std btn-block btn-download">Download</a> - </div> - </div> - </div> -</header> -<!--Header End--> -<!--Navigation Begin--> -<div class="navbar" role="banner"> - <div class="container-fluid"> - <div class="navbar-header"> - <button class="navbar-toggle" type="button" data-toggle="collapse" data-target=".bs-navbar-collapse"> - <span class="icon-bar"></span> - <span class="icon-bar"></span> - <span class="icon-bar"></span> - </button> - </div> - <nav class="collapse navbar-collapse bs-navbar-collapse" role="navigation"> - <ul class="nav navbar-nav"> - <li><a href="/index.html" id="home">Home</a></li> - <li><a href="/getting-help.html" id="getting-help">Getting Help</a></li> - <li><a href="/about/integrates.html" id="project-info">Project Information</a></li> - <li class="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" id="documentation">Documentation <b class="caret"></b></a> - <ul class="dropdown-menu"> - - - <li><a href="/releases/2.0.0-SNAPSHOT/index.html">2.0.0-SNAPSHOT</a></li> - - - - <li><a href="/releases/1.2.0/index.html">1.2.0</a></li> - - - - <li><a href="/releases/1.1.2/index.html">1.1.2</a></li> - - - - <li><a href="/releases/1.1.1/index.html">1.1.1</a></li> - - - - <li><a href="/releases/1.1.0/index.html">1.1.0</a></li> - - - - - - <li><a href="/releases/1.0.6/index.html">1.0.6</a></li> - - - - <li><a href="/releases/1.0.4/index.html">1.0.4</a></li> - - - - - - <li><a href="/releases/1.0.3/index.html">1.0.3</a></li> - - - - - - - - - - <li><a href="/releases/0.10.2/index.html">0.10.2</a></li> - - - - <li><a href="/releases/0.10.1/index.html">0.10.1</a></li> - - - - - - - - <li><a href="/releases/0.9.7/index.html">0.9.7</a></li> - - - - <li><a href="/releases/0.9.6/index.html">0.9.6</a></li> - - - - - - - - - - - - - </ul> - </li> - <li><a href="/talksAndVideos.html">Talks and Slideshows</a></li> - <li class="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" id="contribute">Community <b class="caret"></b></a> - <ul class="dropdown-menu"> - <li><a href="/contribute/Contributing-to-Storm.html">Contributing</a></li> - <li><a href="/contribute/People.html">People</a></li> - <li><a href="/contribute/BYLAWS.html">ByLaws</a></li> - </ul> - </li> - <li><a href="/2018/02/15/storm120-released.html" id="news">News</a></li> - </ul> - </nav> - </div> -</div> - - - - <div class="container-fluid"> - <h1 class="page-title"></h1> - <div class="row"> - <div class="col-md-12"> - <!-- Documentation --> - -<p class="post-meta"></p> - -<ul> -<li><strong>DSLs for non-JVM languages:</strong> These DSL's should be all-inclusive and not require any Java for the creation of topologies, spouts, or bolts. Since topologies are <a href="http://thrift.apache.org/";>Thrift</a> structs, Nimbus is a Thrift service, and bolts can be written in any language, this is possible.</li> -<li><strong>Online machine learning algorithms:</strong> Something like <a href="http://mahout.apache.org/";>Mahout</a> but for online algorithms</li> -<li><strong>Suite of performance benchmarks:</strong> These benchmarks should test Storm's performance on CPU and IO intensive workloads. There should be benchmarks for different classes of applications, such as stream processing (where throughput is the priority) and distributed RPC (where latency is the priority). </li> -</ul> - - - - </div> - </div> - </div> -<footer> - <div class="container-fluid"> - <div class="row"> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>Meetups</h5> - <ul class="latest-news"> - - <li><a href="http://www.meetup.com/Apache-Storm-Apache-Kafka/";>Apache Storm & Apache Kafka</a> <span class="small">(Sunnyvale, CA)</span></li> - - <li><a href="http://www.meetup.com/Apache-Storm-Kafka-Users/";>Apache Storm & Kafka Users</a> <span class="small">(Seattle, WA)</span></li> - - <li><a href="http://www.meetup.com/New-York-City-Storm-User-Group/";>NYC Storm User Group</a> <span class="small">(New York, NY)</span></li> - - <li><a href="http://www.meetup.com/Bay-Area-Stream-Processing";>Bay Area Stream Processing</a> <span class="small">(Emeryville, CA)</span></li> - - <li><a href="http://www.meetup.com/Boston-Storm-Users/";>Boston Realtime Data</a> <span class="small">(Boston, MA)</span></li> - - <li><a href="http://www.meetup.com/storm-london";>London Storm User Group</a> <span class="small">(London, UK)</span></li> - - <!-- <li><a href="http://www.meetup.com/Apache-Storm-Kafka-Users/";>Seatle, WA</a> <span class="small">(27 Jun 2015)</span></li> --> - </ul> - </div> - </div> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>About Storm</h5> - <p>Storm integrates with any queueing system and any database system. Storm's spout abstraction makes it easy to integrate a new queuing system. Likewise, integrating Storm with database systems is easy.</p> - </div> - </div> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>First Look</h5> - <ul class="footer-list"> - <li><a href="/releases/current/Rationale.html">Rationale</a></li> - <li><a href="/releases/current/Tutorial.html">Tutorial</a></li> - <li><a href="/releases/current/Setting-up-development-environment.html">Setting up development environment</a></li> - <li><a href="/releases/current/Creating-a-new-Storm-project.html">Creating a new Storm project</a></li> - </ul> - </div> - </div> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>Documentation</h5> - <ul class="footer-list"> - <li><a href="/releases/current/index.html">Index</a></li> - <li><a href="/releases/current/javadocs/index.html">Javadoc</a></li> - <li><a href="/releases/current/FAQ.html">FAQ</a></li> - </ul> - </div> - </div> - </div> - <hr/> - <div class="row"> - <div class="col-md-12"> - <p align="center">Copyright © 2015 <a href="http://www.apache.org";>Apache Software Foundation</a>. All Rights Reserved. - <br>Apache Storm, Apache, the Apache feather logo, and the Apache Storm project logos are trademarks of The Apache Software Foundation. - <br>All other marks mentioned may be trademarks or registered trademarks of their respective owners.</p> - </div> - </div> - </div> -</footer> -<!--Footer End--> -<!-- Scroll to top --> -<span class="totop"><a href="#"><i class="fa fa-angle-up"></i></a></span> - -</body> - -</html> -
http://git-wip-us.apache.org/repos/asf/storm-site/blob/ff14ea94/content/releases/0.10.1/documentation/Rationale.html ---------------------------------------------------------------------- diff --git a/content/releases/0.10.1/documentation/Rationale.html b/content/releases/0.10.1/documentation/Rationale.html deleted file mode 100644 index f14273d..0000000 --- a/content/releases/0.10.1/documentation/Rationale.html +++ /dev/null @@ -1,282 +0,0 @@ -<!DOCTYPE html> -<html> - <head> - <meta charset="utf-8"> - <meta http-equiv="X-UA-Compatible" content="IE=edge"> - <meta name="viewport" content="width=device-width, initial-scale=1"> - - <link rel="shortcut icon" href="/favicon.ico" type="image/x-icon"> - <link rel="icon" href="/favicon.ico" type="image/x-icon"> - - <title>Rationale</title> - - <!-- Bootstrap core CSS --> - <link href="/assets/css/bootstrap.min.css" rel="stylesheet"> - <!-- Bootstrap theme --> - <link href="/assets/css/bootstrap-theme.min.css" rel="stylesheet"> - - <!-- Custom styles for this template --> - <link rel="stylesheet" href="http://fortawesome.github.io/Font-Awesome/assets/font-awesome/css/font-awesome.css";> - <link href="/css/style.css" rel="stylesheet"> - <link href="/assets/css/owl.theme.css" rel="stylesheet"> - <link href="/assets/css/owl.carousel.css" rel="stylesheet"> - <script type="text/javascript" src="/assets/js/jquery.min.js"></script> - <script type="text/javascript" src="/assets/js/bootstrap.min.js"></script> - <script type="text/javascript" src="/assets/js/owl.carousel.min.js"></script> - <script type="text/javascript" src="/assets/js/storm.js"></script> - <!-- Just for debugging purposes. Don't actually copy these 2 lines! --> - <!--[if lt IE 9]><script src="../../assets/js/ie8-responsive-file-warning.js"></script><![endif]--> - - <!-- HTML5 shim and Respond.js for IE8 support of HTML5 elements and media queries --> - <!--[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> - <header> - <div class="container-fluid"> - <div class="row"> - <div class="col-md-5"> - <a href="/index.html"><img src="/images/logo.png" class="logo" /></a> - </div> - <div class="col-md-5"> - - <h1>Version: 0.10.1</h1> - - </div> - <div class="col-md-2"> - <a href="/downloads.html" class="btn-std btn-block btn-download">Download</a> - </div> - </div> - </div> -</header> -<!--Header End--> -<!--Navigation Begin--> -<div class="navbar" role="banner"> - <div class="container-fluid"> - <div class="navbar-header"> - <button class="navbar-toggle" type="button" data-toggle="collapse" data-target=".bs-navbar-collapse"> - <span class="icon-bar"></span> - <span class="icon-bar"></span> - <span class="icon-bar"></span> - </button> - </div> - <nav class="collapse navbar-collapse bs-navbar-collapse" role="navigation"> - <ul class="nav navbar-nav"> - <li><a href="/index.html" id="home">Home</a></li> - <li><a href="/getting-help.html" id="getting-help">Getting Help</a></li> - <li><a href="/about/integrates.html" id="project-info">Project Information</a></li> - <li class="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" id="documentation">Documentation <b class="caret"></b></a> - <ul class="dropdown-menu"> - - - <li><a href="/releases/2.0.0-SNAPSHOT/index.html">2.0.0-SNAPSHOT</a></li> - - - - <li><a href="/releases/1.2.0/index.html">1.2.0</a></li> - - - - <li><a href="/releases/1.1.2/index.html">1.1.2</a></li> - - - - <li><a href="/releases/1.1.1/index.html">1.1.1</a></li> - - - - <li><a href="/releases/1.1.0/index.html">1.1.0</a></li> - - - - - - <li><a href="/releases/1.0.6/index.html">1.0.6</a></li> - - - - <li><a href="/releases/1.0.4/index.html">1.0.4</a></li> - - - - - - <li><a href="/releases/1.0.3/index.html">1.0.3</a></li> - - - - - - - - - - <li><a href="/releases/0.10.2/index.html">0.10.2</a></li> - - - - <li><a href="/releases/0.10.1/index.html">0.10.1</a></li> - - - - - - - - <li><a href="/releases/0.9.7/index.html">0.9.7</a></li> - - - - <li><a href="/releases/0.9.6/index.html">0.9.6</a></li> - - - - - - - - - - - - - </ul> - </li> - <li><a href="/talksAndVideos.html">Talks and Slideshows</a></li> - <li class="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" id="contribute">Community <b class="caret"></b></a> - <ul class="dropdown-menu"> - <li><a href="/contribute/Contributing-to-Storm.html">Contributing</a></li> - <li><a href="/contribute/People.html">People</a></li> - <li><a href="/contribute/BYLAWS.html">ByLaws</a></li> - </ul> - </li> - <li><a href="/2018/02/15/storm120-released.html" id="news">News</a></li> - </ul> - </nav> - </div> -</div> - - - - <div class="container-fluid"> - <h1 class="page-title">Rationale</h1> - <div class="row"> - <div class="col-md-12"> - <!-- Documentation --> - -<p class="post-meta"></p> - -<p>The past decade has seen a revolution in data processing. MapReduce, Hadoop, and related technologies have made it possible to store and process data at scales previously unthinkable. Unfortunately, these data processing technologies are not realtime systems, nor are they meant to be. There's no hack that will turn Hadoop into a realtime system; realtime data processing has a fundamentally different set of requirements than batch processing.</p> - -<p>However, realtime data processing at massive scale is becoming more and more of a requirement for businesses. The lack of a "Hadoop of realtime" has become the biggest hole in the data processing ecosystem.</p> - -<p>Storm fills that hole.</p> - -<p>Before Storm, you would typically have to manually build a network of queues and workers to do realtime processing. Workers would process messages off a queue, update databases, and send new messages to other queues for further processing. Unfortunately, this approach has serious limitations:</p> - -<ol> -<li><strong>Tedious</strong>: You spend most of your development time configuring where to send messages, deploying workers, and deploying intermediate queues. The realtime processing logic that you care about corresponds to a relatively small percentage of your codebase.</li> -<li><strong>Brittle</strong>: There's little fault-tolerance. You're responsible for keeping each worker and queue up.</li> -<li><strong>Painful to scale</strong>: When the message throughput get too high for a single worker or queue, you need to partition how the data is spread around. You need to reconfigure the other workers to know the new locations to send messages. This introduces moving parts and new pieces that can fail.</li> -</ol> - -<p>Although the queues and workers paradigm breaks down for large numbers of messages, message processing is clearly the fundamental paradigm for realtime computation. The question is: how do you do it in a way that doesn't lose data, scales to huge volumes of messages, and is dead-simple to use and operate?</p> - -<p>Storm satisfies these goals. </p> - -<h2 id="why-storm-is-important">Why Storm is important</h2> - -<p>Storm exposes a set of primitives for doing realtime computation. Like how MapReduce greatly eases the writing of parallel batch processing, Storm's primitives greatly ease the writing of parallel realtime computation.</p> - -<p>The key properties of Storm are:</p> - -<ol> -<li><strong>Extremely broad set of use cases</strong>: Storm can be used for processing messages and updating databases (stream processing), doing a continuous query on data streams and streaming the results into clients (continuous computation), parallelizing an intense query like a search query on the fly (distributed RPC), and more. Storm's small set of primitives satisfy a stunning number of use cases.</li> -<li><strong>Scalable</strong>: Storm scales to massive numbers of messages per second. To scale a topology, all you have to do is add machines and increase the parallelism settings of the topology. As an example of Storm's scale, one of Storm's initial applications processed 1,000,000 messages per second on a 10 node cluster, including hundreds of database calls per second as part of the topology. Storm's usage of Zookeeper for cluster coordination makes it scale to much larger cluster sizes.</li> -<li><strong>Guarantees no data loss</strong>: A realtime system must have strong guarantees about data being successfully processed. A system that drops data has a very limited set of use cases. Storm guarantees that every message will be processed, and this is in direct contrast with other systems like S4. </li> -<li><strong>Extremely robust</strong>: Unlike systems like Hadoop, which are notorious for being difficult to manage, Storm clusters just work. It is an explicit goal of the Storm project to make the user experience of managing Storm clusters as painless as possible.</li> -<li><strong>Fault-tolerant</strong>: If there are faults during execution of your computation, Storm will reassign tasks as necessary. Storm makes sure that a computation can run forever (or until you kill the computation).</li> -<li><strong>Programming language agnostic</strong>: Robust and scalable realtime processing shouldn't be limited to a single platform. Storm topologies and processing components can be defined in any language, making Storm accessible to nearly anyone.</li> -</ol> - - - - </div> - </div> - </div> -<footer> - <div class="container-fluid"> - <div class="row"> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>Meetups</h5> - <ul class="latest-news"> - - <li><a href="http://www.meetup.com/Apache-Storm-Apache-Kafka/";>Apache Storm & Apache Kafka</a> <span class="small">(Sunnyvale, CA)</span></li> - - <li><a href="http://www.meetup.com/Apache-Storm-Kafka-Users/";>Apache Storm & Kafka Users</a> <span class="small">(Seattle, WA)</span></li> - - <li><a href="http://www.meetup.com/New-York-City-Storm-User-Group/";>NYC Storm User Group</a> <span class="small">(New York, NY)</span></li> - - <li><a href="http://www.meetup.com/Bay-Area-Stream-Processing";>Bay Area Stream Processing</a> <span class="small">(Emeryville, CA)</span></li> - - <li><a href="http://www.meetup.com/Boston-Storm-Users/";>Boston Realtime Data</a> <span class="small">(Boston, MA)</span></li> - - <li><a href="http://www.meetup.com/storm-london";>London Storm User Group</a> <span class="small">(London, UK)</span></li> - - <!-- <li><a href="http://www.meetup.com/Apache-Storm-Kafka-Users/";>Seatle, WA</a> <span class="small">(27 Jun 2015)</span></li> --> - </ul> - </div> - </div> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>About Storm</h5> - <p>Storm integrates with any queueing system and any database system. Storm's spout abstraction makes it easy to integrate a new queuing system. Likewise, integrating Storm with database systems is easy.</p> - </div> - </div> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>First Look</h5> - <ul class="footer-list"> - <li><a href="/releases/current/Rationale.html">Rationale</a></li> - <li><a href="/releases/current/Tutorial.html">Tutorial</a></li> - <li><a href="/releases/current/Setting-up-development-environment.html">Setting up development environment</a></li> - <li><a href="/releases/current/Creating-a-new-Storm-project.html">Creating a new Storm project</a></li> - </ul> - </div> - </div> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>Documentation</h5> - <ul class="footer-list"> - <li><a href="/releases/current/index.html">Index</a></li> - <li><a href="/releases/current/javadocs/index.html">Javadoc</a></li> - <li><a href="/releases/current/FAQ.html">FAQ</a></li> - </ul> - </div> - </div> - </div> - <hr/> - <div class="row"> - <div class="col-md-12"> - <p align="center">Copyright © 2015 <a href="http://www.apache.org";>Apache Software Foundation</a>. All Rights Reserved. - <br>Apache Storm, Apache, the Apache feather logo, and the Apache Storm project logos are trademarks of The Apache Software Foundation. - <br>All other marks mentioned may be trademarks or registered trademarks of their respective owners.</p> - </div> - </div> - </div> -</footer> -<!--Footer End--> -<!-- Scroll to top --> -<span class="totop"><a href="#"><i class="fa fa-angle-up"></i></a></span> - -</body> - -</html> - http://git-wip-us.apache.org/repos/asf/storm-site/blob/ff14ea94/content/releases/0.10.1/documentation/Running-topologies-on-a-production-cluster.html ---------------------------------------------------------------------- diff --git a/content/releases/0.10.1/documentation/Running-topologies-on-a-production-cluster.html b/content/releases/0.10.1/documentation/Running-topologies-on-a-production-cluster.html deleted file mode 100644 index 9fc4959..0000000 --- a/content/releases/0.10.1/documentation/Running-topologies-on-a-production-cluster.html +++ /dev/null @@ -1,318 +0,0 @@ -<!DOCTYPE html> -<html> - <head> - <meta charset="utf-8"> - <meta http-equiv="X-UA-Compatible" content="IE=edge"> - <meta name="viewport" content="width=device-width, initial-scale=1"> - - <link rel="shortcut icon" href="/favicon.ico" type="image/x-icon"> - <link rel="icon" href="/favicon.ico" type="image/x-icon"> - - <title>Running Topologies on a Production Cluster</title> - - <!-- Bootstrap core CSS --> - <link href="/assets/css/bootstrap.min.css" rel="stylesheet"> - <!-- Bootstrap theme --> - <link href="/assets/css/bootstrap-theme.min.css" rel="stylesheet"> - - <!-- Custom styles for this template --> - <link rel="stylesheet" href="http://fortawesome.github.io/Font-Awesome/assets/font-awesome/css/font-awesome.css";> - <link href="/css/style.css" rel="stylesheet"> - <link href="/assets/css/owl.theme.css" rel="stylesheet"> - <link href="/assets/css/owl.carousel.css" rel="stylesheet"> - <script type="text/javascript" src="/assets/js/jquery.min.js"></script> - <script type="text/javascript" src="/assets/js/bootstrap.min.js"></script> - <script type="text/javascript" src="/assets/js/owl.carousel.min.js"></script> - <script type="text/javascript" src="/assets/js/storm.js"></script> - <!-- Just for debugging purposes. Don't actually copy these 2 lines! --> - <!--[if lt IE 9]><script src="../../assets/js/ie8-responsive-file-warning.js"></script><![endif]--> - - <!-- HTML5 shim and Respond.js for IE8 support of HTML5 elements and media queries --> - <!--[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> - <header> - <div class="container-fluid"> - <div class="row"> - <div class="col-md-5"> - <a href="/index.html"><img src="/images/logo.png" class="logo" /></a> - </div> - <div class="col-md-5"> - - <h1>Version: 0.10.1</h1> - - </div> - <div class="col-md-2"> - <a href="/downloads.html" class="btn-std btn-block btn-download">Download</a> - </div> - </div> - </div> -</header> -<!--Header End--> -<!--Navigation Begin--> -<div class="navbar" role="banner"> - <div class="container-fluid"> - <div class="navbar-header"> - <button class="navbar-toggle" type="button" data-toggle="collapse" data-target=".bs-navbar-collapse"> - <span class="icon-bar"></span> - <span class="icon-bar"></span> - <span class="icon-bar"></span> - </button> - </div> - <nav class="collapse navbar-collapse bs-navbar-collapse" role="navigation"> - <ul class="nav navbar-nav"> - <li><a href="/index.html" id="home">Home</a></li> - <li><a href="/getting-help.html" id="getting-help">Getting Help</a></li> - <li><a href="/about/integrates.html" id="project-info">Project Information</a></li> - <li class="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" id="documentation">Documentation <b class="caret"></b></a> - <ul class="dropdown-menu"> - - - <li><a href="/releases/2.0.0-SNAPSHOT/index.html">2.0.0-SNAPSHOT</a></li> - - - - <li><a href="/releases/1.2.0/index.html">1.2.0</a></li> - - - - <li><a href="/releases/1.1.2/index.html">1.1.2</a></li> - - - - <li><a href="/releases/1.1.1/index.html">1.1.1</a></li> - - - - <li><a href="/releases/1.1.0/index.html">1.1.0</a></li> - - - - - - <li><a href="/releases/1.0.6/index.html">1.0.6</a></li> - - - - <li><a href="/releases/1.0.4/index.html">1.0.4</a></li> - - - - - - <li><a href="/releases/1.0.3/index.html">1.0.3</a></li> - - - - - - - - - - <li><a href="/releases/0.10.2/index.html">0.10.2</a></li> - - - - <li><a href="/releases/0.10.1/index.html">0.10.1</a></li> - - - - - - - - <li><a href="/releases/0.9.7/index.html">0.9.7</a></li> - - - - <li><a href="/releases/0.9.6/index.html">0.9.6</a></li> - - - - - - - - - - - - - </ul> - </li> - <li><a href="/talksAndVideos.html">Talks and Slideshows</a></li> - <li class="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" id="contribute">Community <b class="caret"></b></a> - <ul class="dropdown-menu"> - <li><a href="/contribute/Contributing-to-Storm.html">Contributing</a></li> - <li><a href="/contribute/People.html">People</a></li> - <li><a href="/contribute/BYLAWS.html">ByLaws</a></li> - </ul> - </li> - <li><a href="/2018/02/15/storm120-released.html" id="news">News</a></li> - </ul> - </nav> - </div> -</div> - - - - <div class="container-fluid"> - <h1 class="page-title">Running Topologies on a Production Cluster</h1> - <div class="row"> - <div class="col-md-12"> - <!-- Documentation --> - -<p class="post-meta"></p> - -<p>Running topologies on a production cluster is similar to running in <a href="Local-mode.html">Local mode</a>. Here are the steps:</p> - -<p>1) Define the topology (Use <a href="/javadoc/apidocs/backtype/storm/topology/TopologyBuilder.html">TopologyBuilder</a> if defining using Java)</p> - -<p>2) Use <a href="/javadoc/apidocs/backtype/storm/StormSubmitter.html">StormSubmitter</a> to submit the topology to the cluster. <code>StormSubmitter</code> takes as input the name of the topology, a configuration for the topology, and the topology itself. For example:</p> -<div class="highlight"><pre><code class="language-java" data-lang="java"><span class="n">Config</span> <span class="n">conf</span> <span class="o">=</span> <span class="k">new</span> <span class="n">Config</span><span class="o">();</span> -<span class="n">conf</span><span class="o">.</span><span class="na">setNumWorkers</span><span class="o">(</span><span class="mi">20</span><span class="o">);</span> -<span class="n">conf</span><span class="o">.</span><span class="na">setMaxSpoutPending</span><span class="o">(</span><span class="mi">5000</span><span class="o">);</span> -<span class="n">StormSubmitter</span><span class="o">.</span><span class="na">submitTopology</span><span class="o">(</span><span class="s">"mytopology"</span><span class="o">,</span> <span class="n">conf</span><span class="o">,</span> <span class="n">topology</span><span class="o">);</span> -</code></pre></div> -<p>3) Create a jar containing your code and all the dependencies of your code (except for Storm -- the Storm jars will be added to the classpath on the worker nodes).</p> - -<p>If you're using Maven, the <a href="http://maven.apache.org/plugins/maven-assembly-plugin/";>Maven Assembly Plugin</a> can do the packaging for you. Just add this to your pom.xml:</p> -<div class="highlight"><pre><code class="language-xml" data-lang="xml"> <span class="nt"><plugin></span> - <span class="nt"><artifactId></span>maven-assembly-plugin<span class="nt"></artifactId></span> - <span class="nt"><configuration></span> - <span class="nt"><descriptorRefs></span> - <span class="nt"><descriptorRef></span>jar-with-dependencies<span class="nt"></descriptorRef></span> - <span class="nt"></descriptorRefs></span> - <span class="nt"><archive></span> - <span class="nt"><manifest></span> - <span class="nt"><mainClass></span>com.path.to.main.Class<span class="nt"></mainClass></span> - <span class="nt"></manifest></span> - <span class="nt"></archive></span> - <span class="nt"></configuration></span> - <span class="nt"></plugin></span> -</code></pre></div> -<p>Then run mvn assembly:assembly to get an appropriately packaged jar. Make sure you <a href="http://maven.apache.org/plugins/maven-assembly-plugin/examples/single/including-and-excluding-artifacts.html";>exclude</a> the Storm jars since the cluster already has Storm on the classpath.</p> - -<p>4) Submit the topology to the cluster using the <code>storm</code> client, specifying the path to your jar, the classname to run, and any arguments it will use:</p> - -<p><code>storm jar path/to/allmycode.jar org.me.MyTopology arg1 arg2 arg3</code></p> - -<p><code>storm jar</code> will submit the jar to the cluster and configure the <code>StormSubmitter</code> class to talk to the right cluster. In this example, after uploading the jar <code>storm jar</code> calls the main function on <code>org.me.MyTopology</code> with the arguments "arg1", "arg2", and "arg3".</p> - -<p>You can find out how to configure your <code>storm</code> client to talk to a Storm cluster on <a href="Setting-up-development-environment.html">Setting up development environment</a>.</p> - -<h3 id="common-configurations">Common configurations</h3> - -<p>There are a variety of configurations you can set per topology. A list of all the configurations you can set can be found <a href="/javadoc/apidocs/backtype/storm/Config.html">here</a>. The ones prefixed with "TOPOLOGY" can be overridden on a topology-specific basis (the other ones are cluster configurations and cannot be overridden). Here are some common ones that are set for a topology:</p> - -<ol> -<li><strong>Config.TOPOLOGY_WORKERS</strong>: This sets the number of worker processes to use to execute the topology. For example, if you set this to 25, there will be 25 Java processes across the cluster executing all the tasks. If you had a combined 150 parallelism across all components in the topology, each worker process will have 6 tasks running within it as threads.</li> -<li><strong>Config.TOPOLOGY_ACKERS</strong>: This sets the number of tasks that will track tuple trees and detect when a spout tuple has been fully processed. Ackers are an integral part of Storm's reliability model and you can read more about them on <a href="Guaranteeing-message-processing.html">Guaranteeing message processing</a>.</li> -<li><strong>Config.TOPOLOGY_MAX_SPOUT_PENDING</strong>: This sets the maximum number of spout tuples that can be pending on a single spout task at once (pending means the tuple has not been acked or failed yet). It is highly recommended you set this config to prevent queue explosion.</li> -<li><strong>Config.TOPOLOGY_MESSAGE_TIMEOUT_SECS</strong>: This is the maximum amount of time a spout tuple has to be fully completed before it is considered failed. This value defaults to 30 seconds, which is sufficient for most topologies. See <a href="Guaranteeing-message-processing.html">Guaranteeing message processing</a> for more information on how Storm's reliability model works.</li> -<li><strong>Config.TOPOLOGY_SERIALIZATIONS</strong>: You can register more serializers to Storm using this config so that you can use custom types within tuples.</li> -</ol> - -<h3 id="killing-a-topology">Killing a topology</h3> - -<p>To kill a topology, simply run:</p> - -<p><code>storm kill {stormname}</code></p> - -<p>Give the same name to <code>storm kill</code> as you used when submitting the topology.</p> - -<p>Storm won't kill the topology immediately. Instead, it deactivates all the spouts so that they don't emit any more tuples, and then Storm waits Config.TOPOLOGY_MESSAGE_TIMEOUT_SECS seconds before destroying all the workers. This gives the topology enough time to complete any tuples it was processing when it got killed.</p> - -<h3 id="updating-a-running-topology">Updating a running topology</h3> - -<p>To update a running topology, the only option currently is to kill the current topology and resubmit a new one. A planned feature is to implement a <code>storm swap</code> command that swaps a running topology with a new one, ensuring minimal downtime and no chance of both topologies processing tuples at the same time. </p> - -<h3 id="monitoring-topologies">Monitoring topologies</h3> - -<p>The best place to monitor a topology is using the Storm UI. The Storm UI provides information about errors happening in tasks and fine-grained stats on the throughput and latency performance of each component of each running topology.</p> - -<p>You can also look at the worker logs on the cluster machines.</p> - - - - </div> - </div> - </div> -<footer> - <div class="container-fluid"> - <div class="row"> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>Meetups</h5> - <ul class="latest-news"> - - <li><a href="http://www.meetup.com/Apache-Storm-Apache-Kafka/";>Apache Storm & Apache Kafka</a> <span class="small">(Sunnyvale, CA)</span></li> - - <li><a href="http://www.meetup.com/Apache-Storm-Kafka-Users/";>Apache Storm & Kafka Users</a> <span class="small">(Seattle, WA)</span></li> - - <li><a href="http://www.meetup.com/New-York-City-Storm-User-Group/";>NYC Storm User Group</a> <span class="small">(New York, NY)</span></li> - - <li><a href="http://www.meetup.com/Bay-Area-Stream-Processing";>Bay Area Stream Processing</a> <span class="small">(Emeryville, CA)</span></li> - - <li><a href="http://www.meetup.com/Boston-Storm-Users/";>Boston Realtime Data</a> <span class="small">(Boston, MA)</span></li> - - <li><a href="http://www.meetup.com/storm-london";>London Storm User Group</a> <span class="small">(London, UK)</span></li> - - <!-- <li><a href="http://www.meetup.com/Apache-Storm-Kafka-Users/";>Seatle, WA</a> <span class="small">(27 Jun 2015)</span></li> --> - </ul> - </div> - </div> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>About Storm</h5> - <p>Storm integrates with any queueing system and any database system. Storm's spout abstraction makes it easy to integrate a new queuing system. Likewise, integrating Storm with database systems is easy.</p> - </div> - </div> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>First Look</h5> - <ul class="footer-list"> - <li><a href="/releases/current/Rationale.html">Rationale</a></li> - <li><a href="/releases/current/Tutorial.html">Tutorial</a></li> - <li><a href="/releases/current/Setting-up-development-environment.html">Setting up development environment</a></li> - <li><a href="/releases/current/Creating-a-new-Storm-project.html">Creating a new Storm project</a></li> - </ul> - </div> - </div> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>Documentation</h5> - <ul class="footer-list"> - <li><a href="/releases/current/index.html">Index</a></li> - <li><a href="/releases/current/javadocs/index.html">Javadoc</a></li> - <li><a href="/releases/current/FAQ.html">FAQ</a></li> - </ul> - </div> - </div> - </div> - <hr/> - <div class="row"> - <div class="col-md-12"> - <p align="center">Copyright © 2015 <a href="http://www.apache.org";>Apache Software Foundation</a>. All Rights Reserved. - <br>Apache Storm, Apache, the Apache feather logo, and the Apache Storm project logos are trademarks of The Apache Software Foundation. - <br>All other marks mentioned may be trademarks or registered trademarks of their respective owners.</p> - </div> - </div> - </div> -</footer> -<!--Footer End--> -<!-- Scroll to top --> -<span class="totop"><a href="#"><i class="fa fa-angle-up"></i></a></span> - -</body> - -</html> - http://git-wip-us.apache.org/repos/asf/storm-site/blob/ff14ea94/content/releases/0.10.1/documentation/Serialization-(prior-to-0.6.0).html ---------------------------------------------------------------------- diff --git a/content/releases/0.10.1/documentation/Serialization-(prior-to-0.6.0).html b/content/releases/0.10.1/documentation/Serialization-(prior-to-0.6.0).html deleted file mode 100644 index 8c78b1b..0000000 --- a/content/releases/0.10.1/documentation/Serialization-(prior-to-0.6.0).html +++ /dev/null @@ -1,294 +0,0 @@ -<!DOCTYPE html> -<html> - <head> - <meta charset="utf-8"> - <meta http-equiv="X-UA-Compatible" content="IE=edge"> - <meta name="viewport" content="width=device-width, initial-scale=1"> - - <link rel="shortcut icon" href="/favicon.ico" type="image/x-icon"> - <link rel="icon" href="/favicon.ico" type="image/x-icon"> - - <title>Serialization (Prior to 0.6.0)</title> - - <!-- Bootstrap core CSS --> - <link href="/assets/css/bootstrap.min.css" rel="stylesheet"> - <!-- Bootstrap theme --> - <link href="/assets/css/bootstrap-theme.min.css" rel="stylesheet"> - - <!-- Custom styles for this template --> - <link rel="stylesheet" href="http://fortawesome.github.io/Font-Awesome/assets/font-awesome/css/font-awesome.css";> - <link href="/css/style.css" rel="stylesheet"> - <link href="/assets/css/owl.theme.css" rel="stylesheet"> - <link href="/assets/css/owl.carousel.css" rel="stylesheet"> - <script type="text/javascript" src="/assets/js/jquery.min.js"></script> - <script type="text/javascript" src="/assets/js/bootstrap.min.js"></script> - <script type="text/javascript" src="/assets/js/owl.carousel.min.js"></script> - <script type="text/javascript" src="/assets/js/storm.js"></script> - <!-- Just for debugging purposes. Don't actually copy these 2 lines! --> - <!--[if lt IE 9]><script src="../../assets/js/ie8-responsive-file-warning.js"></script><![endif]--> - - <!-- HTML5 shim and Respond.js for IE8 support of HTML5 elements and media queries --> - <!--[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> - <header> - <div class="container-fluid"> - <div class="row"> - <div class="col-md-5"> - <a href="/index.html"><img src="/images/logo.png" class="logo" /></a> - </div> - <div class="col-md-5"> - - <h1>Version: 0.10.1</h1> - - </div> - <div class="col-md-2"> - <a href="/downloads.html" class="btn-std btn-block btn-download">Download</a> - </div> - </div> - </div> -</header> -<!--Header End--> -<!--Navigation Begin--> -<div class="navbar" role="banner"> - <div class="container-fluid"> - <div class="navbar-header"> - <button class="navbar-toggle" type="button" data-toggle="collapse" data-target=".bs-navbar-collapse"> - <span class="icon-bar"></span> - <span class="icon-bar"></span> - <span class="icon-bar"></span> - </button> - </div> - <nav class="collapse navbar-collapse bs-navbar-collapse" role="navigation"> - <ul class="nav navbar-nav"> - <li><a href="/index.html" id="home">Home</a></li> - <li><a href="/getting-help.html" id="getting-help">Getting Help</a></li> - <li><a href="/about/integrates.html" id="project-info">Project Information</a></li> - <li class="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" id="documentation">Documentation <b class="caret"></b></a> - <ul class="dropdown-menu"> - - - <li><a href="/releases/2.0.0-SNAPSHOT/index.html">2.0.0-SNAPSHOT</a></li> - - - - <li><a href="/releases/1.2.0/index.html">1.2.0</a></li> - - - - <li><a href="/releases/1.1.2/index.html">1.1.2</a></li> - - - - <li><a href="/releases/1.1.1/index.html">1.1.1</a></li> - - - - <li><a href="/releases/1.1.0/index.html">1.1.0</a></li> - - - - - - <li><a href="/releases/1.0.6/index.html">1.0.6</a></li> - - - - <li><a href="/releases/1.0.4/index.html">1.0.4</a></li> - - - - - - <li><a href="/releases/1.0.3/index.html">1.0.3</a></li> - - - - - - - - - - <li><a href="/releases/0.10.2/index.html">0.10.2</a></li> - - - - <li><a href="/releases/0.10.1/index.html">0.10.1</a></li> - - - - - - - - <li><a href="/releases/0.9.7/index.html">0.9.7</a></li> - - - - <li><a href="/releases/0.9.6/index.html">0.9.6</a></li> - - - - - - - - - - - - - </ul> - </li> - <li><a href="/talksAndVideos.html">Talks and Slideshows</a></li> - <li class="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" id="contribute">Community <b class="caret"></b></a> - <ul class="dropdown-menu"> - <li><a href="/contribute/Contributing-to-Storm.html">Contributing</a></li> - <li><a href="/contribute/People.html">People</a></li> - <li><a href="/contribute/BYLAWS.html">ByLaws</a></li> - </ul> - </li> - <li><a href="/2018/02/15/storm120-released.html" id="news">News</a></li> - </ul> - </nav> - </div> -</div> - - - - <div class="container-fluid"> - <h1 class="page-title">Serialization (Prior to 0.6.0)</h1> - <div class="row"> - <div class="col-md-12"> - <!-- Documentation --> - -<p class="post-meta"></p> - -<p>Tuples can be comprised of objects of any types. Since Storm is a distributed system, it needs to know how to serialize and deserialize objects when they're passed between tasks. By default Storm can serialize ints, shorts, longs, floats, doubles, bools, bytes, strings, and byte arrays, but if you want to use another type in your tuples, you'll need to implement a custom serializer.</p> - -<h3 id="dynamic-typing">Dynamic typing</h3> - -<p>There are no type declarations for fields in a Tuple. You put objects in fields and Storm figures out the serialization dynamically. Before we get to the interface for serialization, let's spend a moment understanding why Storm's tuples are dynamically typed.</p> - -<p>Adding static typing to tuple fields would add large amount of complexity to Storm's API. Hadoop, for example, statically types its keys and values but requires a huge amount of annotations on the part of the user. Hadoop's API is a burden to use and the "type safety" isn't worth it. Dynamic typing is simply easier to use.</p> - -<p>Further than that, it's not possible to statically type Storm's tuples in any reasonable way. Suppose a Bolt subscribes to multiple streams. The tuples from all those streams may have different types across the fields. When a Bolt receives a <code>Tuple</code> in <code>execute</code>, that tuple could have come from any stream and so could have any combination of types. There might be some reflection magic you can do to declare a different method for every tuple stream a bolt subscribes to, but Storm opts for the simpler, straightforward approach of dynamic typing.</p> - -<p>Finally, another reason for using dynamic typing is so Storm can be used in a straightforward manner from dynamically typed languages like Clojure and JRuby.</p> - -<h3 id="custom-serialization">Custom serialization</h3> - -<p>Let's dive into Storm's API for defining custom serializations. There are two steps you need to take as a user to create a custom serialization: implement the serializer, and register the serializer to Storm.</p> - -<h4 id="creating-a-serializer">Creating a serializer</h4> - -<p>Custom serializers implement the <a href="/javadoc/apidocs/backtype/storm/serialization/ISerialization.html">ISerialization</a> interface. Implementations specify how to serialize and deserialize types into a binary format.</p> - -<p>The interface looks like this:</p> -<div class="highlight"><pre><code class="language-java" data-lang="java"><span class="kd">public</span> <span class="kd">interface</span> <span class="nc">ISerialization</span><span class="o"><</span><span class="n">T</span><span class="o">></span> <span class="o">{</span> - <span class="kd">public</span> <span class="kt">boolean</span> <span class="nf">accept</span><span class="o">(</span><span class="n">Class</span> <span class="n">c</span><span class="o">);</span> - <span class="kd">public</span> <span class="kt">void</span> <span class="nf">serialize</span><span class="o">(</span><span class="n">T</span> <span class="n">object</span><span class="o">,</span> <span class="n">DataOutputStream</span> <span class="n">stream</span><span class="o">)</span> <span class="kd">throws</span> <span class="n">IOException</span><span class="o">;</span> - <span class="kd">public</span> <span class="n">T</span> <span class="nf">deserialize</span><span class="o">(</span><span class="n">DataInputStream</span> <span class="n">stream</span><span class="o">)</span> <span class="kd">throws</span> <span class="n">IOException</span><span class="o">;</span> -<span class="o">}</span> -</code></pre></div> -<p>Storm uses the <code>accept</code> method to determine if a type can be serialized by this serializer. Remember, Storm's tuples are dynamically typed so Storm determines what serializer to use at runtime.</p> - -<p><code>serialize</code> writes the object out to the output stream in binary format. The field must be written in a way such that it can be deserialized later. For example, if you're writing out a list of objects, you'll need to write out the size of the list first so that you know how many elements to deserialize.</p> - -<p><code>deserialize</code> reads the serialized object off of the stream and returns it.</p> - -<p>You can see example serialization implementations in the source for <a href="https://github.com/apache/storm/blob/0.5.4/src/jvm/backtype/storm/serialization/SerializationFactory.java";>SerializationFactory</a></p> - -<h4 id="registering-a-serializer">Registering a serializer</h4> - -<p>Once you create a serializer, you need to tell Storm it exists. This is done through the Storm configuration (See <a href="Concepts.html">Concepts</a> for information about how configuration works in Storm). You can register serializations either through the config given when submitting a topology or in the storm.yaml files across your cluster.</p> - -<p>Serializer registrations are done through the Config.TOPOLOGY_SERIALIZATIONS config and is simply a list of serialization class names.</p> - -<p>Storm provides helpers for registering serializers in a topology config. The <a href="/javadoc/apidocs/backtype/storm/Config.html">Config</a> class has a method called <code>addSerialization</code> that takes in a serializer class to add to the config.</p> - -<p>There's an advanced config called Config.TOPOLOGY_SKIP_MISSING_SERIALIZATIONS. If you set this to true, Storm will ignore any serializations that are registered but do not have their code available on the classpath. Otherwise, Storm will throw errors when it can't find a serialization. This is useful if you run many topologies on a cluster that each have different serializations, but you want to declare all the serializations across all topologies in the <code>storm.yaml</code> files.</p> - - - - </div> - </div> - </div> -<footer> - <div class="container-fluid"> - <div class="row"> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>Meetups</h5> - <ul class="latest-news"> - - <li><a href="http://www.meetup.com/Apache-Storm-Apache-Kafka/";>Apache Storm & Apache Kafka</a> <span class="small">(Sunnyvale, CA)</span></li> - - <li><a href="http://www.meetup.com/Apache-Storm-Kafka-Users/";>Apache Storm & Kafka Users</a> <span class="small">(Seattle, WA)</span></li> - - <li><a href="http://www.meetup.com/New-York-City-Storm-User-Group/";>NYC Storm User Group</a> <span class="small">(New York, NY)</span></li> - - <li><a href="http://www.meetup.com/Bay-Area-Stream-Processing";>Bay Area Stream Processing</a> <span class="small">(Emeryville, CA)</span></li> - - <li><a href="http://www.meetup.com/Boston-Storm-Users/";>Boston Realtime Data</a> <span class="small">(Boston, MA)</span></li> - - <li><a href="http://www.meetup.com/storm-london";>London Storm User Group</a> <span class="small">(London, UK)</span></li> - - <!-- <li><a href="http://www.meetup.com/Apache-Storm-Kafka-Users/";>Seatle, WA</a> <span class="small">(27 Jun 2015)</span></li> --> - </ul> - </div> - </div> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>About Storm</h5> - <p>Storm integrates with any queueing system and any database system. Storm's spout abstraction makes it easy to integrate a new queuing system. Likewise, integrating Storm with database systems is easy.</p> - </div> - </div> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>First Look</h5> - <ul class="footer-list"> - <li><a href="/releases/current/Rationale.html">Rationale</a></li> - <li><a href="/releases/current/Tutorial.html">Tutorial</a></li> - <li><a href="/releases/current/Setting-up-development-environment.html">Setting up development environment</a></li> - <li><a href="/releases/current/Creating-a-new-Storm-project.html">Creating a new Storm project</a></li> - </ul> - </div> - </div> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>Documentation</h5> - <ul class="footer-list"> - <li><a href="/releases/current/index.html">Index</a></li> - <li><a href="/releases/current/javadocs/index.html">Javadoc</a></li> - <li><a href="/releases/current/FAQ.html">FAQ</a></li> - </ul> - </div> - </div> - </div> - <hr/> - <div class="row"> - <div class="col-md-12"> - <p align="center">Copyright © 2015 <a href="http://www.apache.org";>Apache Software Foundation</a>. All Rights Reserved. - <br>Apache Storm, Apache, the Apache feather logo, and the Apache Storm project logos are trademarks of The Apache Software Foundation. - <br>All other marks mentioned may be trademarks or registered trademarks of their respective owners.</p> - </div> - </div> - </div> -</footer> -<!--Footer End--> -<!-- Scroll to top --> -<span class="totop"><a href="#"><i class="fa fa-angle-up"></i></a></span> - -</body> - -</html> - http://git-wip-us.apache.org/repos/asf/storm-site/blob/ff14ea94/content/releases/0.10.1/documentation/Serialization.html ---------------------------------------------------------------------- diff --git a/content/releases/0.10.1/documentation/Serialization.html b/content/releases/0.10.1/documentation/Serialization.html deleted file mode 100644 index bc4098f..0000000 --- a/content/releases/0.10.1/documentation/Serialization.html +++ /dev/null @@ -1,306 +0,0 @@ -<!DOCTYPE html> -<html> - <head> - <meta charset="utf-8"> - <meta http-equiv="X-UA-Compatible" content="IE=edge"> - <meta name="viewport" content="width=device-width, initial-scale=1"> - - <link rel="shortcut icon" href="/favicon.ico" type="image/x-icon"> - <link rel="icon" href="/favicon.ico" type="image/x-icon"> - - <title>Serialization</title> - - <!-- Bootstrap core CSS --> - <link href="/assets/css/bootstrap.min.css" rel="stylesheet"> - <!-- Bootstrap theme --> - <link href="/assets/css/bootstrap-theme.min.css" rel="stylesheet"> - - <!-- Custom styles for this template --> - <link rel="stylesheet" href="http://fortawesome.github.io/Font-Awesome/assets/font-awesome/css/font-awesome.css";> - <link href="/css/style.css" rel="stylesheet"> - <link href="/assets/css/owl.theme.css" rel="stylesheet"> - <link href="/assets/css/owl.carousel.css" rel="stylesheet"> - <script type="text/javascript" src="/assets/js/jquery.min.js"></script> - <script type="text/javascript" src="/assets/js/bootstrap.min.js"></script> - <script type="text/javascript" src="/assets/js/owl.carousel.min.js"></script> - <script type="text/javascript" src="/assets/js/storm.js"></script> - <!-- Just for debugging purposes. Don't actually copy these 2 lines! --> - <!--[if lt IE 9]><script src="../../assets/js/ie8-responsive-file-warning.js"></script><![endif]--> - - <!-- HTML5 shim and Respond.js for IE8 support of HTML5 elements and media queries --> - <!--[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> - <header> - <div class="container-fluid"> - <div class="row"> - <div class="col-md-5"> - <a href="/index.html"><img src="/images/logo.png" class="logo" /></a> - </div> - <div class="col-md-5"> - - <h1>Version: 0.10.1</h1> - - </div> - <div class="col-md-2"> - <a href="/downloads.html" class="btn-std btn-block btn-download">Download</a> - </div> - </div> - </div> -</header> -<!--Header End--> -<!--Navigation Begin--> -<div class="navbar" role="banner"> - <div class="container-fluid"> - <div class="navbar-header"> - <button class="navbar-toggle" type="button" data-toggle="collapse" data-target=".bs-navbar-collapse"> - <span class="icon-bar"></span> - <span class="icon-bar"></span> - <span class="icon-bar"></span> - </button> - </div> - <nav class="collapse navbar-collapse bs-navbar-collapse" role="navigation"> - <ul class="nav navbar-nav"> - <li><a href="/index.html" id="home">Home</a></li> - <li><a href="/getting-help.html" id="getting-help">Getting Help</a></li> - <li><a href="/about/integrates.html" id="project-info">Project Information</a></li> - <li class="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" id="documentation">Documentation <b class="caret"></b></a> - <ul class="dropdown-menu"> - - - <li><a href="/releases/2.0.0-SNAPSHOT/index.html">2.0.0-SNAPSHOT</a></li> - - - - <li><a href="/releases/1.2.0/index.html">1.2.0</a></li> - - - - <li><a href="/releases/1.1.2/index.html">1.1.2</a></li> - - - - <li><a href="/releases/1.1.1/index.html">1.1.1</a></li> - - - - <li><a href="/releases/1.1.0/index.html">1.1.0</a></li> - - - - - - <li><a href="/releases/1.0.6/index.html">1.0.6</a></li> - - - - <li><a href="/releases/1.0.4/index.html">1.0.4</a></li> - - - - - - <li><a href="/releases/1.0.3/index.html">1.0.3</a></li> - - - - - - - - - - <li><a href="/releases/0.10.2/index.html">0.10.2</a></li> - - - - <li><a href="/releases/0.10.1/index.html">0.10.1</a></li> - - - - - - - - <li><a href="/releases/0.9.7/index.html">0.9.7</a></li> - - - - <li><a href="/releases/0.9.6/index.html">0.9.6</a></li> - - - - - - - - - - - - - </ul> - </li> - <li><a href="/talksAndVideos.html">Talks and Slideshows</a></li> - <li class="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" id="contribute">Community <b class="caret"></b></a> - <ul class="dropdown-menu"> - <li><a href="/contribute/Contributing-to-Storm.html">Contributing</a></li> - <li><a href="/contribute/People.html">People</a></li> - <li><a href="/contribute/BYLAWS.html">ByLaws</a></li> - </ul> - </li> - <li><a href="/2018/02/15/storm120-released.html" id="news">News</a></li> - </ul> - </nav> - </div> -</div> - - - - <div class="container-fluid"> - <h1 class="page-title">Serialization</h1> - <div class="row"> - <div class="col-md-12"> - <!-- Documentation --> - -<p class="post-meta"></p> - -<p>This page is about how the serialization system in Storm works for versions 0.6.0 and onwards. Storm used a different serialization system prior to 0.6.0 which is documented on <a href="Serialization-(prior-to-0.6.0).html">Serialization (prior to 0.6.0)</a>. </p> - -<p>Tuples can be comprised of objects of any types. Since Storm is a distributed system, it needs to know how to serialize and deserialize objects when they're passed between tasks.</p> - -<p>Storm uses <a href="http://code.google.com/p/kryo/";>Kryo</a> for serialization. Kryo is a flexible and fast serialization library that produces small serializations.</p> - -<p>By default, Storm can serialize primitive types, strings, byte arrays, ArrayList, HashMap, HashSet, and the Clojure collection types. If you want to use another type in your tuples, you'll need to register a custom serializer.</p> - -<h3 id="dynamic-typing">Dynamic typing</h3> - -<p>There are no type declarations for fields in a Tuple. You put objects in fields and Storm figures out the serialization dynamically. Before we get to the interface for serialization, let's spend a moment understanding why Storm's tuples are dynamically typed.</p> - -<p>Adding static typing to tuple fields would add large amount of complexity to Storm's API. Hadoop, for example, statically types its keys and values but requires a huge amount of annotations on the part of the user. Hadoop's API is a burden to use and the "type safety" isn't worth it. Dynamic typing is simply easier to use.</p> - -<p>Further than that, it's not possible to statically type Storm's tuples in any reasonable way. Suppose a Bolt subscribes to multiple streams. The tuples from all those streams may have different types across the fields. When a Bolt receives a <code>Tuple</code> in <code>execute</code>, that tuple could have come from any stream and so could have any combination of types. There might be some reflection magic you can do to declare a different method for every tuple stream a bolt subscribes to, but Storm opts for the simpler, straightforward approach of dynamic typing.</p> - -<p>Finally, another reason for using dynamic typing is so Storm can be used in a straightforward manner from dynamically typed languages like Clojure and JRuby.</p> - -<h3 id="custom-serialization">Custom serialization</h3> - -<p>As mentioned, Storm uses Kryo for serialization. To implement custom serializers, you need to register new serializers with Kryo. It's highly recommended that you read over <a href="http://code.google.com/p/kryo/";>Kryo's home page</a> to understand how it handles custom serialization.</p> - -<p>Adding custom serializers is done through the "topology.kryo.register" property in your topology config. It takes a list of registrations, where each registration can take one of two forms:</p> - -<ol> -<li>The name of a class to register. In this case, Storm will use Kryo's <code>FieldsSerializer</code> to serialize the class. This may or may not be optimal for the class -- see the Kryo docs for more details.</li> -<li>A map from the name of a class to register to an implementation of <a href="http://code.google.com/p/kryo/source/browse/trunk/src/com/esotericsoftware/kryo/Serializer.java";>com.esotericsoftware.kryo.Serializer</a>.</li> -</ol> - -<p>Let's look at an example.</p> -<div class="highlight"><pre><code class="language-" data-lang="">topology.kryo.register: - - com.mycompany.CustomType1 - - com.mycompany.CustomType2: com.mycompany.serializer.CustomType2Serializer - - com.mycompany.CustomType3 -</code></pre></div> -<p><code>com.mycompany.CustomType1</code> and <code>com.mycompany.CustomType3</code> will use the <code>FieldsSerializer</code>, whereas <code>com.mycompany.CustomType2</code> will use <code>com.mycompany.serializer.CustomType2Serializer</code> for serialization.</p> - -<p>Storm provides helpers for registering serializers in a topology config. The <a href="/javadoc/apidocs/backtype/storm/Config.html">Config</a> class has a method called <code>registerSerialization</code> that takes in a registration to add to the config.</p> - -<p>There's an advanced config called <code>Config.TOPOLOGY_SKIP_MISSING_KRYO_REGISTRATIONS</code>. If you set this to true, Storm will ignore any serializations that are registered but do not have their code available on the classpath. Otherwise, Storm will throw errors when it can't find a serialization. This is useful if you run many topologies on a cluster that each have different serializations, but you want to declare all the serializations across all topologies in the <code>storm.yaml</code> files.</p> - -<h3 id="java-serialization">Java serialization</h3> - -<p>If Storm encounters a type for which it doesn't have a serialization registered, it will use Java serialization if possible. If the object can't be serialized with Java serialization, then Storm will throw an error.</p> - -<p>Beware that Java serialization is extremely expensive, both in terms of CPU cost as well as the size of the serialized object. It is highly recommended that you register custom serializers when you put the topology in production. The Java serialization behavior is there so that it's easy to prototype new topologies.</p> - -<p>You can turn off the behavior to fall back on Java serialization by setting the <code>Config.TOPOLOGY_FALL_BACK_ON_JAVA_SERIALIZATION</code> config to false.</p> - -<h3 id="component-specific-serialization-registrations">Component-specific serialization registrations</h3> - -<p>Storm 0.7.0 lets you set component-specific configurations (read more about this at <a href="Configuration.html">Configuration</a>). Of course, if one component defines a serialization that serialization will need to be available to other bolts -- otherwise they won't be able to receive messages from that component!</p> - -<p>When a topology is submitted, a single set of serializations is chosen to be used by all components in the topology for sending messages. This is done by merging the component-specific serializer registrations with the regular set of serialization registrations. If two components define serializers for the same class, one of the serializers is chosen arbitrarily.</p> - -<p>To force a serializer for a particular class if there's a conflict between two component-specific registrations, just define the serializer you want to use in the topology-specific configuration. The topology-specific configuration has precedence over component-specific configurations for serialization registrations.</p> - - - - </div> - </div> - </div> -<footer> - <div class="container-fluid"> - <div class="row"> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>Meetups</h5> - <ul class="latest-news"> - - <li><a href="http://www.meetup.com/Apache-Storm-Apache-Kafka/";>Apache Storm & Apache Kafka</a> <span class="small">(Sunnyvale, CA)</span></li> - - <li><a href="http://www.meetup.com/Apache-Storm-Kafka-Users/";>Apache Storm & Kafka Users</a> <span class="small">(Seattle, WA)</span></li> - - <li><a href="http://www.meetup.com/New-York-City-Storm-User-Group/";>NYC Storm User Group</a> <span class="small">(New York, NY)</span></li> - - <li><a href="http://www.meetup.com/Bay-Area-Stream-Processing";>Bay Area Stream Processing</a> <span class="small">(Emeryville, CA)</span></li> - - <li><a href="http://www.meetup.com/Boston-Storm-Users/";>Boston Realtime Data</a> <span class="small">(Boston, MA)</span></li> - - <li><a href="http://www.meetup.com/storm-london";>London Storm User Group</a> <span class="small">(London, UK)</span></li> - - <!-- <li><a href="http://www.meetup.com/Apache-Storm-Kafka-Users/";>Seatle, WA</a> <span class="small">(27 Jun 2015)</span></li> --> - </ul> - </div> - </div> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>About Storm</h5> - <p>Storm integrates with any queueing system and any database system. Storm's spout abstraction makes it easy to integrate a new queuing system. Likewise, integrating Storm with database systems is easy.</p> - </div> - </div> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>First Look</h5> - <ul class="footer-list"> - <li><a href="/releases/current/Rationale.html">Rationale</a></li> - <li><a href="/releases/current/Tutorial.html">Tutorial</a></li> - <li><a href="/releases/current/Setting-up-development-environment.html">Setting up development environment</a></li> - <li><a href="/releases/current/Creating-a-new-Storm-project.html">Creating a new Storm project</a></li> - </ul> - </div> - </div> - <div class="col-md-3"> - <div class="footer-widget"> - <h5>Documentation</h5> - <ul class="footer-list"> - <li><a href="/releases/current/index.html">Index</a></li> - <li><a href="/releases/current/javadocs/index.html">Javadoc</a></li> - <li><a href="/releases/current/FAQ.html">FAQ</a></li> - </ul> - </div> - </div> - </div> - <hr/> - <div class="row"> - <div class="col-md-12"> - <p align="center">Copyright © 2015 <a href="http://www.apache.org";>Apache Software Foundation</a>. All Rights Reserved. - <br>Apache Storm, Apache, the Apache feather logo, and the Apache Storm project logos are trademarks of The Apache Software Foundation. - <br>All other marks mentioned may be trademarks or registered trademarks of their respective owners.</p> - </div> - </div> - </div> -</footer> -<!--Footer End--> -<!-- Scroll to top --> -<span class="totop"><a href="#"><i class="fa fa-angle-up"></i></a></span> - -</body> - -</html> -
