 




<?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: Comparing VM performance to physical servers</title>
	<atom:link href="http://itknowledgeexchange.techtarget.com/itanswers/comparing-vm-performance-to-physical-servers/feed/" rel="self" type="application/rss+xml" />
	<link>http://itknowledgeexchange.techtarget.com/itanswers/comparing-vm-performance-to-physical-servers/</link>
	<description></description>
	<lastBuildDate>Tue, 21 May 2013 18:28:49 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	
	<item>
		<title>By: anil desai</title>
		<link>http://itknowledgeexchange.techtarget.com/itanswers/comparing-vm-performance-to-physical-servers/#comment-52862</link>
		<dc:creator>anil desai</dc:creator>
		<pubDate>Mon, 21 Apr 2008 14:58:48 +0000</pubDate>
		<guid isPermaLink="false">#comment-52862</guid>
		<description><![CDATA[Unfortunately, there&#039;s no single number that can be used to demonstrate the amount of overhead for the many different types of guest OS&#039;s and applications you&#039;ll be deploying.  In general, most organizations will find that the performance trade-off is minimal when compared to the cost savings and other benefits of moving to virtualization.  If you really want numbers for planning purposes, you can try running standard CPU, memory, disk, and network benchmarks on a host server and within a VM on the host server.  Of course, the challenge will be in translating this to &quot;real world&quot; impacts - something that often requires adequate performance monitoring and testing.  In general, for most business applications, you&#039;re unlikely to run into insurmountable performance issues with VMs.]]></description>
		<content:encoded><![CDATA[<p>Unfortunately, there&#8217;s no single number that can be used to demonstrate the amount of overhead for the many different types of guest OS&#8217;s and applications you&#8217;ll be deploying.  In general, most organizations will find that the performance trade-off is minimal when compared to the cost savings and other benefits of moving to virtualization.  If you really want numbers for planning purposes, you can try running standard CPU, memory, disk, and network benchmarks on a host server and within a VM on the host server.  Of course, the challenge will be in translating this to &#8220;real world&#8221; impacts &#8211; something that often requires adequate performance monitoring and testing.  In general, for most business applications, you&#8217;re unlikely to run into insurmountable performance issues with VMs.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: amaltemara</title>
		<link>http://itknowledgeexchange.techtarget.com/itanswers/comparing-vm-performance-to-physical-servers/#comment-52842</link>
		<dc:creator>amaltemara</dc:creator>
		<pubDate>Sat, 19 Apr 2008 05:36:11 +0000</pubDate>
		<guid isPermaLink="false">#comment-52842</guid>
		<description><![CDATA[The overhead with virtualization depends greatly on the virtualization technology.

Solutions that install onto the &#039;bare metal&#039; without a Host OS will perform the best most of the time (VMware ESX being one), with solutions that install onto another OS taking much more of a hit. (VMware Server / Virtual PC).

You have to really consider your environment and objective, and look for the solution that fits.

There are virtualization platforms for web hosting that work just for Linux OSs, and can share the same OS filesystem, but run separate environments and kernels in memory. These solutions run even faster than ESX server, but only run 1 version of the OS.

VirtualServer is free, but has to be installed on another OS, such as linux or windows. It has the disadvantage of much more overhead, but has the advantage of being able to use the hardware compatibility of the host OS.  Virtualization solutions that run on the &#039;bare-metal&#039; without a host OS are fast, but only support a select group of hardware, because they must write their own device drivers specifically for their solution.]]></description>
		<content:encoded><![CDATA[<p>The overhead with virtualization depends greatly on the virtualization technology.</p>
<p>Solutions that install onto the &#8216;bare metal&#8217; without a Host OS will perform the best most of the time (VMware ESX being one), with solutions that install onto another OS taking much more of a hit. (VMware Server / Virtual PC).</p>
<p>You have to really consider your environment and objective, and look for the solution that fits.</p>
<p>There are virtualization platforms for web hosting that work just for Linux OSs, and can share the same OS filesystem, but run separate environments and kernels in memory. These solutions run even faster than ESX server, but only run 1 version of the OS.</p>
<p>VirtualServer is free, but has to be installed on another OS, such as linux or windows. It has the disadvantage of much more overhead, but has the advantage of being able to use the hardware compatibility of the host OS.  Virtualization solutions that run on the &#8216;bare-metal&#8217; without a host OS are fast, but only support a select group of hardware, because they must write their own device drivers specifically for their solution.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

<!-- Performance optimized by W3 Total Cache. Learn more: http://www.w3-edge.com/wordpress-plugins/

Page Caching using memcached
Database Caching 3/10 queries in 0.041 seconds using memcached
Object Caching 281/287 objects using memcached

Served from: itknowledgeexchange.techtarget.com @ 2013-05-21 19:15:17 -->