<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Life Scaling &#187; Performance</title>
	<atom:link href="http://orensol.com/tag/performance/feed/" rel="self" type="application/rss+xml" />
	<link>http://orensol.com</link>
	<description>Oren Solomianik's Blog</description>
	<lastBuildDate>Mon, 21 Jun 2010 08:10:03 +0000</lastBuildDate>
	<generator>http://wordpress.org/?v=2.8.4</generator>
	<language>en</language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
			<item>
		<title>Network Latency Inside And Across Amazon EC2 Availability Zones</title>
		<link>http://orensol.com/2009/05/24/network-latency-inside-and-across-amazon-ec2-availability-zones/</link>
		<comments>http://orensol.com/2009/05/24/network-latency-inside-and-across-amazon-ec2-availability-zones/#comments</comments>
		<pubDate>Sun, 24 May 2009 12:40:55 +0000</pubDate>
		<dc:creator>Oren</dc:creator>
				<category><![CDATA[Cloud Computing]]></category>
		<category><![CDATA[EC2]]></category>
		<category><![CDATA[LAMP]]></category>
		<category><![CDATA[Scaling]]></category>
		<category><![CDATA[Availability Zones]]></category>
		<category><![CDATA[Clusters]]></category>
		<category><![CDATA[High Availability]]></category>
		<category><![CDATA[latency]]></category>
		<category><![CDATA[Network]]></category>
		<category><![CDATA[Performance]]></category>
		<category><![CDATA[ping]]></category>
		<category><![CDATA[RTT]]></category>
		<category><![CDATA[throughput]]></category>

		<guid isPermaLink="false">http://orensol.com/?p=226</guid>
		<description><![CDATA[<p>I couldn&#8217;t find any info out there comparing network latency across <a target="_blank" href="http://aws.amazon.com/ec2/">EC2 Availability Zones</a> and inside any single Availability Zone. So I took 6 instances (2 on each US zone), ran some test using a simple ping, and measured 10 Round Trip Times (<a target="_blank" href="http://en.wikipedia.org/wiki/Round-trip_delay_time">RTT</a>). Here are the results.</p>
Single Availablity Zone Latency



Availability [...]]]></description>
			<content:encoded><![CDATA[<p>I couldn&#8217;t find any info out there comparing network latency across <a target="_blank" href="http://aws.amazon.com/ec2/">EC2 Availability Zones</a> and inside any single Availability Zone. So I took 6 instances (2 on each US zone), ran some test using a simple ping, and measured 10 Round Trip Times (<a target="_blank" href="http://en.wikipedia.org/wiki/Round-trip_delay_time">RTT</a>). Here are the results.</p>
<h3>Single Availablity Zone Latency</h3>
<table border="0">
<tbody>
<tr>
<th>Availability Zone</th>
<th>Minimum RTT</th>
<th>Maximum RTT</th>
<th>Average RTT</th>
</tr>
<tr>
<td>us-east-1a</td>
<td>0.215ms</td>
<td>0.348ms</td>
<td>0.263ms</td>
</tr>
<tr>
<td>us-east-1b</td>
<td>0.200ms</td>
<td>0.327ms</td>
<td>0.259ms</td>
</tr>
<tr>
<td>us-east-1c</td>
<td>0.342ms</td>
<td>0.556ms</td>
<td>0.410ms</td>
</tr>
</tbody>
</table>
<p>It seems that at the time of my testing, zone us-east-1c had the worst RTT between 2 instances in it, almost twice as slow as the other 2 zones.</p>
<h3>Cross Availablity Zone Latency</h3>
<table border="0">
<tbody>
<tr>
<th>Availability Zones</th>
<th>Minimum RTT</th>
<th>Maximum RTT</th>
<th>Average RTT</th>
</tr>
<tr>
<td>Between us-east-1a and us-east-1b</td>
<td>0.885ms</td>
<td>1.110ms</td>
<td>0.937ms</td>
</tr>
<tr>
<td>Between us-east-1a and us-east-1c</td>
<td>0.937ms</td>
<td>1.080ms</td>
<td>1.031ms</td>
</tr>
<tr>
<td>Between us-east-1b and us-east-1c</td>
<td>1.060ms</td>
<td>1.250ms</td>
<td>1.126ms</td>
</tr>
</tbody>
</table>
<p>It&#8217;s worth noting that in cross availability zones traffic, the first ping was usually off the chart, so I disregarded it. For example, it could be anywhere between 300ms to 400ms, and the the rest would fall down to ~0.300. Probably some lazy routing techniques by Amazon&#8217;s routers.</p>
<h3>Conclusions</h3>
<ol>
<li>Zones are created different! &#8212; At least at the time of the testing, if you have a cluster on us-east-1b it performs almost twice as fast with regards to RTT between machines than a cluster on us-east-1c.</li>
<li>Cross Availability Zones latency can be 6 times higher than inner zone latency. For a network intensive application, better keep your instances crowded in the same zone.</li>
</ol>
<p>I should probably also make a throughput comparison between and across Availability Zones. I promise to share if I get to test it.</p>
]]></content:encoded>
			<wfw:commentRss>http://orensol.com/2009/05/24/network-latency-inside-and-across-amazon-ec2-availability-zones/feed/</wfw:commentRss>
		<slash:comments>3</slash:comments>
		</item>
	</channel>
</rss>
<!-- WP Super Cache is installed but broken. The path to wp-cache-phase1.php in wp-content/advanced-cache.php must be fixed! -->