| <!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"> |
| <meta name="description" content="The Apache Cassandra database is the right choice when you need scalability and high availability without compromising performance. Linear scalability and proven fault-tolerance on commodity hardware or cloud infrastructure make it the perfect platform for mission-critical data. Cassandra's support for replicating across multiple datacenters is best-in-class, providing lower latency for your users and the peace of mind of knowing that you can survive regional outages. |
| "> |
| <meta name="keywords" content="cassandra, apache, apache cassandra, distributed storage, key value store, scalability, bigtable, dynamo" /> |
| <meta name="robots" content="index,follow" /> |
| <meta name="language" content="en" /> |
| |
| <title>Documentation</title> |
| |
| <link rel="canonical" href="http://cassandra.apache.org/doc/3.10/architecture/dynamo.html"> |
| |
| <link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/css/bootstrap.min.css" integrity="sha384-1q8mTJOASx8j1Au+a5WDVnPi2lkFfwwEAa8hDDdjZlpLegxhjVME1fgjWPGmkzs7" crossorigin="anonymous"> |
| <link rel="stylesheet" href="./../../../css/style.css"> |
| |
| <link rel="stylesheet" href="./../../../css/sphinx.css"> |
| |
| |
| <link rel="top" title="Apache Cassandra Documentation v3.10" href="../index.html"/> <link rel="up" title="Architecture" href="index.html"/> <link rel="next" title="Storage Engine" href="storage_engine.html"/> <link rel="prev" title="Overview" href="overview.html"/> |
| </head> |
| |
| <body> |
| <!-- breadcrumbs --> |
| <div class="topnav"> |
| <div class="container breadcrumb-container"> |
| <ul class="breadcrumb"> |
| <li> |
| <div class="dropdown"> |
| <img class="asf-logo" src="./../../../img/asf_feather.png" /> |
| <a data-toggle="dropdown" href="#">Apache Software Foundation <span class="caret"></span></a> |
| <ul class="dropdown-menu" role="menu" aria-labelledby="dLabel"> |
| <li><a href="http://www.apache.org">Apache Homepage</a></li> |
| <li><a href="http://www.apache.org/licenses/">License</a></li> |
| <li><a href="http://www.apache.org/foundation/sponsorship.html">Sponsorship</a></li> |
| <li><a href="http://www.apache.org/foundation/thanks.html">Thanks</a></li> |
| <li><a href="http://www.apache.org/security/">Security</a></li> |
| </ul> |
| </div> |
| </li> |
| |
| |
| <li><a href="./../../../">Apache Cassandra</a></li> |
| |
| |
| |
| |
| <li><a href="./../../../doc">Documentation</a></li> |
| |
| |
| |
| |
| <li><a href="./">Architecture</a></li> |
| |
| |
| |
| <li>Dynamo</li> |
| |
| </ul> |
| </div> |
| |
| <!-- navbar --> |
| <nav class="navbar navbar-default navbar-static-top" role="navigation"> |
| <div class="container"> |
| <div class="navbar-header"> |
| <button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#cassandra-menu" aria-expanded="false"> |
| <span class="sr-only">Toggle navigation</span> |
| <span class="icon-bar"></span> |
| <span class="icon-bar"></span> |
| <span class="icon-bar"></span> |
| </button> |
| <a class="navbar-brand" href="./../../../"><img src="./../../../img/cassandra_logo.png" alt="Apache Cassandra logo" /></a> |
| </div><!-- /.navbar-header --> |
| |
| <div id="cassandra-menu" class="collapse navbar-collapse"> |
| <ul class="nav navbar-nav navbar-right"> |
| <li><a href="./../../../">Home</a></li> |
| <li><a href="./../../../download/">Download</a></li> |
| <li><a href="./../../../doc/">Documentation</a></li> |
| <li><a href="./../../../community/">Community</a></li> |
| </ul> |
| </div><!-- /#cassandra-menu --> |
| |
| |
| </div> |
| </nav><!-- /.navbar --> |
| </div><!-- /.topnav --> |
| |
| <div class="container-fluid"> |
| <div class="row"> |
| <div class="col-md-2"> |
| <div class="doc-navigation"> |
| <div class="doc-menu" role="navigation"> |
| <div class="navbar-header"> |
| <button type="button" class="pull-left navbar-toggle" data-toggle="collapse" data-target=".sidebar-navbar-collapse"> |
| <span class="sr-only">Toggle navigation</span> |
| <span class="icon-bar"></span> |
| <span class="icon-bar"></span> |
| <span class="icon-bar"></span> |
| </button> |
| </div> |
| <div class="navbar-collapse collapse sidebar-navbar-collapse"> |
| <form id="doc-search-form" class="navbar-form" action="../search.html" method="get" role="search"> |
| <div class="form-group"> |
| <input type="text" size="30" class="form-control input-sm" name="q" placeholder="Search docs"> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </div> |
| </form> |
| |
| |
| |
| <ul class="current"> |
| <li class="toctree-l1"><a class="reference internal" href="../getting_started/index.html">Getting Started</a></li> |
| <li class="toctree-l1 current"><a class="reference internal" href="index.html">Architecture</a><ul class="current"> |
| <li class="toctree-l2"><a class="reference internal" href="overview.html">Overview</a></li> |
| <li class="toctree-l2 current"><a class="current reference internal" href="#">Dynamo</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="#gossip">Gossip</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="#failure-detection">Failure Detection</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="#token-ring-ranges">Token Ring/Ranges</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="#replication">Replication</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="#tunable-consistency">Tunable Consistency</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="storage_engine.html">Storage Engine</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="guarantees.html">Guarantees</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l1"><a class="reference internal" href="../data_modeling/index.html">Data Modeling</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../cql/index.html">The Cassandra Query Language (CQL)</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../configuration/index.html">Configuring Cassandra</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../operating/index.html">Operating Cassandra</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../tools/index.html">Cassandra Tools</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../troubleshooting/index.html">Troubleshooting</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../development/index.html">Cassandra Development</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../faq/index.html">Frequently Asked Questions</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../bugs.html">Reporting Bugs and Contributing</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../contactus.html">Contact us</a></li> |
| </ul> |
| |
| |
| |
| </div><!--/.nav-collapse --> |
| </div> |
| </div> |
| </div> |
| <div class="col-md-8"> |
| <div class="content doc-content"> |
| <div class="container"> |
| |
| <div class="section" id="dynamo"> |
| <h1>Dynamo<a class="headerlink" href="#dynamo" title="Permalink to this headline">ΒΆ</a></h1> |
| <div class="section" id="gossip"> |
| <span id="id1"></span><h2>Gossip<a class="headerlink" href="#gossip" title="Permalink to this headline">ΒΆ</a></h2> |
| <div class="admonition-todo admonition" id="index-0"> |
| <p class="first admonition-title">Todo</p> |
| <p class="last">todo</p> |
| </div> |
| </div> |
| <div class="section" id="failure-detection"> |
| <h2>Failure Detection<a class="headerlink" href="#failure-detection" title="Permalink to this headline">ΒΆ</a></h2> |
| <div class="admonition-todo admonition" id="index-1"> |
| <p class="first admonition-title">Todo</p> |
| <p class="last">todo</p> |
| </div> |
| </div> |
| <div class="section" id="token-ring-ranges"> |
| <h2>Token Ring/Ranges<a class="headerlink" href="#token-ring-ranges" title="Permalink to this headline">ΒΆ</a></h2> |
| <div class="admonition-todo admonition" id="index-2"> |
| <p class="first admonition-title">Todo</p> |
| <p class="last">todo</p> |
| </div> |
| </div> |
| <div class="section" id="replication"> |
| <span id="replication-strategy"></span><h2>Replication<a class="headerlink" href="#replication" title="Permalink to this headline">ΒΆ</a></h2> |
| <p>The replication strategy of a keyspace determines which nodes are replicas for a given token range. The two main |
| replication strategies are <a class="reference internal" href="#simple-strategy"><span class="std std-ref">SimpleStrategy</span></a> and <a class="reference internal" href="#network-topology-strategy"><span class="std std-ref">NetworkTopologyStrategy</span></a>.</p> |
| <div class="section" id="simplestrategy"> |
| <span id="simple-strategy"></span><h3>SimpleStrategy<a class="headerlink" href="#simplestrategy" title="Permalink to this headline">ΒΆ</a></h3> |
| <p>SimpleStrategy allows a single integer <code class="docutils literal"><span class="pre">replication_factor</span></code> to be defined. This determines the number of nodes that |
| should contain a copy of each row. For example, if <code class="docutils literal"><span class="pre">replication_factor</span></code> is 3, then three different nodes should store |
| a copy of each row.</p> |
| <p>SimpleStrategy treats all nodes identically, ignoring any configured datacenters or racks. To determine the replicas |
| for a token range, Cassandra iterates through the tokens in the ring, starting with the token range of interest. For |
| each token, it checks whether the owning node has been added to the set of replicas, and if it has not, it is added to |
| the set. This process continues until <code class="docutils literal"><span class="pre">replication_factor</span></code> distinct nodes have been added to the set of replicas.</p> |
| </div> |
| <div class="section" id="networktopologystrategy"> |
| <span id="network-topology-strategy"></span><h3>NetworkTopologyStrategy<a class="headerlink" href="#networktopologystrategy" title="Permalink to this headline">ΒΆ</a></h3> |
| <p>NetworkTopologyStrategy allows a replication factor to be specified for each datacenter in the cluster. Even if your |
| cluster only uses a single datacenter, NetworkTopologyStrategy should be prefered over SimpleStrategy to make it easier |
| to add new physical or virtual datacenters to the cluster later.</p> |
| <p>In addition to allowing the replication factor to be specified per-DC, NetworkTopologyStrategy also attempts to choose |
| replicas within a datacenter from different racks. If the number of racks is greater than or equal to the replication |
| factor for the DC, each replica will be chosen from a different rack. Otherwise, each rack will hold at least one |
| replica, but some racks may hold more than one. Note that this rack-aware behavior has some potentially <a class="reference external" href="https://issues.apache.org/jira/browse/CASSANDRA-3810">surprising |
| implications</a>. For example, if there are not an even number of |
| nodes in each rack, the data load on the smallest rack may be much higher. Similarly, if a single node is bootstrapped |
| into a new rack, it will be considered a replica for the entire ring. For this reason, many operators choose to |
| configure all nodes on a single “rack”.</p> |
| </div> |
| </div> |
| <div class="section" id="tunable-consistency"> |
| <h2>Tunable Consistency<a class="headerlink" href="#tunable-consistency" title="Permalink to this headline">ΒΆ</a></h2> |
| <p>Cassandra supports a per-operation tradeoff between consistency and availability through <em>Consistency Levels</em>. |
| Essentially, an operation’s consistency level specifies how many of the replicas need to respond to the coordinator in |
| order to consider the operation a success.</p> |
| <p>The following consistency levels are available:</p> |
| <dl class="docutils"> |
| <dt><code class="docutils literal"><span class="pre">ONE</span></code></dt> |
| <dd>Only a single replica must respond.</dd> |
| <dt><code class="docutils literal"><span class="pre">TWO</span></code></dt> |
| <dd>Two replicas must respond.</dd> |
| <dt><code class="docutils literal"><span class="pre">THREE</span></code></dt> |
| <dd>Three replicas must respond.</dd> |
| <dt><code class="docutils literal"><span class="pre">QUORUM</span></code></dt> |
| <dd>A majority (n/2 + 1) of the replicas must respond.</dd> |
| <dt><code class="docutils literal"><span class="pre">ALL</span></code></dt> |
| <dd>All of the replicas must respond.</dd> |
| <dt><code class="docutils literal"><span class="pre">LOCAL_QUORUM</span></code></dt> |
| <dd>A majority of the replicas in the local datacenter (whichever datacenter the coordinator is in) must respond.</dd> |
| <dt><code class="docutils literal"><span class="pre">EACH_QUORUM</span></code></dt> |
| <dd>A majority of the replicas in each datacenter must respond.</dd> |
| <dt><code class="docutils literal"><span class="pre">LOCAL_ONE</span></code></dt> |
| <dd>Only a single replica must respond. In a multi-datacenter cluster, this also gaurantees that read requests are not |
| sent to replicas in a remote datacenter.</dd> |
| <dt><code class="docutils literal"><span class="pre">ANY</span></code></dt> |
| <dd>A single replica may respond, or the coordinator may store a hint. If a hint is stored, the coordinator will later |
| attempt to replay the hint and deliver the mutation to the replicas. This consistency level is only accepted for |
| write operations.</dd> |
| </dl> |
| <p>Write operations are always sent to all replicas, regardless of consistency level. The consistency level simply |
| controls how many responses the coordinator waits for before responding to the client.</p> |
| <p>For read operations, the coordinator generally only issues read commands to enough replicas to satisfy the consistency |
| level. There are a couple of exceptions to this:</p> |
| <ul class="simple"> |
| <li>Speculative retry may issue a redundant read request to an extra replica if the other replicas have not responded |
| within a specified time window.</li> |
| <li>Based on <code class="docutils literal"><span class="pre">read_repair_chance</span></code> and <code class="docutils literal"><span class="pre">dclocal_read_repair_chance</span></code> (part of a table’s schema), read requests may be |
| randomly sent to all replicas in order to repair potentially inconsistent data.</li> |
| </ul> |
| <div class="section" id="picking-consistency-levels"> |
| <h3>Picking Consistency Levels<a class="headerlink" href="#picking-consistency-levels" title="Permalink to this headline">ΒΆ</a></h3> |
| <p>It is common to pick read and write consistency levels that are high enough to overlap, resulting in “strong” |
| consistency. This is typically expressed as <code class="docutils literal"><span class="pre">W</span> <span class="pre">+</span> <span class="pre">R</span> <span class="pre">></span> <span class="pre">RF</span></code>, where <code class="docutils literal"><span class="pre">W</span></code> is the write consistency level, <code class="docutils literal"><span class="pre">R</span></code> is the |
| read consistency level, and <code class="docutils literal"><span class="pre">RF</span></code> is the replication factor. For example, if <code class="docutils literal"><span class="pre">RF</span> <span class="pre">=</span> <span class="pre">3</span></code>, a <code class="docutils literal"><span class="pre">QUORUM</span></code> request will |
| require responses from at least two of the three replicas. If <code class="docutils literal"><span class="pre">QUORUM</span></code> is used for both writes and reads, at least |
| one of the replicas is guaranteed to participate in <em>both</em> the write and the read request, which in turn guarantees that |
| the latest write will be read. In a multi-datacenter environment, <code class="docutils literal"><span class="pre">LOCAL_QUORUM</span></code> can be used to provide a weaker but |
| still useful guarantee: reads are guaranteed to see the latest write from within the same datacenter.</p> |
| <p>If this type of strong consistency isn’t required, lower consistency levels like <code class="docutils literal"><span class="pre">ONE</span></code> may be used to improve |
| throughput, latency, and availability.</p> |
| </div> |
| </div> |
| </div> |
| |
| |
| |
| |
| <div class="doc-prev-next-links" role="navigation" aria-label="footer navigation"> |
| |
| <a href="storage_engine.html" class="btn btn-default pull-right " role="button" title="Storage Engine" accesskey="n">Next <span class="glyphicon glyphicon-circle-arrow-right" aria-hidden="true"></span></a> |
| |
| |
| <a href="overview.html" class="btn btn-default" role="button" title="Overview" accesskey="p"><span class="glyphicon glyphicon-circle-arrow-left" aria-hidden="true"></span> Previous</a> |
| |
| </div> |
| |
| </div> |
| </div> |
| </div> |
| <div class="col-md-2"> |
| </div> |
| </div> |
| </div> |
| |
| <footer> |
| <div class="container"> |
| <div class="col-md-4 social-blk"> |
| <span class="social"> |
| <a href="https://twitter.com/cassandra" |
| class="twitter-follow-button" |
| data-show-count="false" data-size="large">Follow @cassandra</a> |
| <script>!function(d,s,id){var js,fjs=d.getElementsByTagName(s)[0],p=/^http:/.test(d.location)?'http':'https';if(!d.getElementById(id)){js=d.createElement(s);js.id=id;js.src=p+'://platform.twitter.com/widgets.js';fjs.parentNode.insertBefore(js,fjs);}}(document, 'script', 'twitter-wjs');</script> |
| <a href="https://twitter.com/intent/tweet?button_hashtag=cassandra" |
| class="twitter-hashtag-button" |
| data-size="large" |
| data-related="ApacheCassandra">Tweet #cassandra</a> |
| <script>!function(d,s,id){var js,fjs=d.getElementsByTagName(s)[0],p=/^http:/.test(d.location)?'http':'https';if(!d.getElementById(id)){js=d.createElement(s);js.id=id;js.src=p+'://platform.twitter.com/widgets.js';fjs.parentNode.insertBefore(js,fjs);}}(document, 'script', 'twitter-wjs');</script> |
| </span> |
| </div> |
| |
| <div class="col-md-8 trademark"> |
| <p>© 2016 <a href="http://apache.org">The Apache Software Foundation</a>. |
| Apache, the Apache feather logo, and Apache Cassandra are trademarks of The Apache Software Foundation. |
| <p> |
| </div> |
| </div><!-- /.container --> |
| </footer> |
| |
| <!-- Javascript. Placed here so pages load faster --> |
| <script src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.3/jquery.min.js"></script> |
| <script src="./../../../js/underscore-min.js"></script> |
| <script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/js/bootstrap.min.js" integrity="sha384-0mSbJDEHialfmuBBQP6A4Qrprq5OVfW37PRR3j5ELqxss1yVqOtnepnHVP9aJ7xS" crossorigin="anonymous"></script> |
| |
| |
| <script src="./../../../js/doctools.js"></script> |
| <script src="./../../../js/searchtools.js"></script> |
| |
| <script type="text/javascript"> var DOCUMENTATION_OPTIONS = { URL_ROOT: "", VERSION: "", COLLAPSE_INDEX: false, FILE_SUFFIX: ".html", HAS_SOURCE: false, SOURCELINK_SUFFIX: "" }; </script> |
| |
| <script type="text/javascript"> |
| $(function() { |
| // Stick the #nav to the top of the window |
| var nav = $('.doc-navigation'); |
| var navHomeY = nav.offset().top; |
| var isFixed = false; |
| var $w = $(window); |
| $w.scroll(function() { |
| var scrollTop = $w.scrollTop(); |
| var shouldBeFixed = $w.width() > 991 && scrollTop >= navHomeY - 10; |
| if (shouldBeFixed && !isFixed) { |
| nav.css({ |
| position: 'fixed', |
| top: 0, |
| left: nav.offset().left, |
| width: nav.width(), |
| }); |
| nav.addClass('fixed-navigation'); |
| isFixed = true; |
| } |
| else if (!shouldBeFixed && isFixed) |
| { |
| nav.css({ |
| position: 'static' |
| }); |
| nav.removeClass('fixed-navigation'); |
| isFixed = false; |
| } |
| }); |
| }); |
| </script> |
| |
| |
| <script type="text/javascript"> |
| var gaJsHost = (("https:" == document.location.protocol) ? "https://ssl." : "http://www."); |
| document.write(unescape("%3Cscript src='" + gaJsHost + "google-analytics.com/ga.js' type='text/javascript'%3E%3C/script%3E")); |
| |
| try { |
| var pageTracker = _gat._getTracker("UA-11583863-1"); |
| pageTracker._trackPageview(); |
| } catch(err) {} |
| </script> |
| |
| |
| </body> |
| </html> |