Fetching contributors…
Cannot retrieve contributors at this time
39 lines (28 sloc) 2.52 KB
<link type="text/css" rel="stylesheet" href="style.css" />
<div id="page">
<div id='header'>
<a href="index.html">
<img style="border:none" alt="Redis Documentation" src="redis.png">
<div id="pagecontent">
<div class="index">
<!-- This is a (PRE) block. Make sure it's left aligned or your toc title will be off. -->
<b>Speed: Contents</b><br>&nbsp;&nbsp;<a href="#Speed (ROUGH DRAFT)">Speed (ROUGH DRAFT)</a><br>&nbsp;&nbsp;&nbsp;&nbsp;<a href="#TODO">TODO</a>
<h1 class="wikiname">Speed</h1>
<div class="summary">
<div class="narrow">
<h1><a name="Speed (ROUGH DRAFT)">Speed (ROUGH DRAFT)</a></h1><h2><a name="TODO">TODO</a></h2><ul><li> Written in ANSI C</li><li> Pipelining</li><li> MultiBulkCommands</li><li> epoll &gt;= 1.1</li><li> Benchmarks</li></ul>
Redis takes the whole dataset in memory and <a href="Persistence.html">writes asynchronously to disk</a> in order to be very fast, you have the best of both worlds: hyper-speed and <a href="Persistence.html">persistence</a> for your data.<br/><br/>Establishing a new connection to a Redis Server is <i>simple</i> and <i>fast</i> nothing more that a TCP three way handshake. There is no authentication or other handshake involved (<a href="" target="_blank">Google Group: Can we use connection pool in Redis?</a>) You can read more about the way Redis clients communicate with servers in the <a href="ProtocolSpecification.html">Protocol Specification</a>.<br/><br/>On most commodity hardware it takes about 45 seconds to restore a 2 GB database, without fancy RAID. This can give you some kind of feeling about the order of magnitude of the time needed to load data when you restart the server, so restarting a server is fast too.<br/><br/>Also <a href="Replication.html">Replication</a> is fast, benchamarks will give you the the same order of magnitude a restart does (<a href="" target="_blank">Google Group: Replication speed benchmak</a>)