<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	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/"
		>
<channel>
	<title>Comments on: Sizing virtual machine hosts</title>
	<atom:link href="http://www.binarywar.com/2009/11/sizing-virtual-machine-hosts/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.binarywar.com/2009/11/sizing-virtual-machine-hosts/</link>
	<description>My KB.  If it helps someone else who is searching for answers...great!</description>
	<lastBuildDate>Fri, 03 Feb 2012 15:07:01 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.0.2</generator>
	<item>
		<title>By: Aaron</title>
		<link>http://www.binarywar.com/2009/11/sizing-virtual-machine-hosts/comment-page-1/#comment-20</link>
		<dc:creator>Aaron</dc:creator>
		<pubDate>Fri, 13 Nov 2009 02:24:13 +0000</pubDate>
		<guid isPermaLink="false">http://www.binarywar.com/2009/11/sizing-virtual-machine-hosts/#comment-20</guid>
		<description>It has to do with SCSI disk locking and the number of hosts accessing the same LUN at the same time.  Over a certain number starts to degrade performance.  I found, through research, that people were recommending 15 - 20 as a general guideline.  I think the amount of space kind of follows that because if you have 30 GB OS disks and you have 20 of them, that is 600 GB.  However, if you have a very demanding application, such as a SQL server, it is worth considering setting up the log files disk using Raw Device Mapping (RDM) so that it has a dedicated LUN and is accessing it directly.  That also eliminates a layer of overhead that is created by having a virtual disk that would, in turn, reside on a LUN.</description>
		<content:encoded><![CDATA[<p>It has to do with SCSI disk locking and the number of hosts accessing the same LUN at the same time.  Over a certain number starts to degrade performance.  I found, through research, that people were recommending 15 &#8211; 20 as a general guideline.  I think the amount of space kind of follows that because if you have 30 GB OS disks and you have 20 of them, that is 600 GB.  However, if you have a very demanding application, such as a SQL server, it is worth considering setting up the log files disk using Raw Device Mapping (RDM) so that it has a dedicated LUN and is accessing it directly.  That also eliminates a layer of overhead that is created by having a virtual disk that would, in turn, reside on a LUN.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Eli</title>
		<link>http://www.binarywar.com/2009/11/sizing-virtual-machine-hosts/comment-page-1/#comment-14</link>
		<dc:creator>Eli</dc:creator>
		<pubDate>Tue, 10 Nov 2009 22:58:02 +0000</pubDate>
		<guid isPermaLink="false">http://www.binarywar.com/2009/11/sizing-virtual-machine-hosts/#comment-14</guid>
		<description>What is the logic behind the 500-600Gb guideline and the 15-20 virtual disks?</description>
		<content:encoded><![CDATA[<p>What is the logic behind the 500-600Gb guideline and the 15-20 virtual disks?</p>
]]></content:encoded>
	</item>
</channel>
</rss>

