<?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: Hello Dynamic Memory?</title>
	<atom:link href="http://www.vcritical.com/2010/02/hello-dynamic-memory/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.vcritical.com/2010/02/hello-dynamic-memory/</link>
	<description>Informed Virtualization Criticism</description>
	<lastBuildDate>Sat, 04 Feb 2012 19:14:33 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.2.1</generator>
	<item>
		<title>By: az első Hyper-v patch kapcs&#225;n</title>
		<link>http://www.vcritical.com/2010/02/hello-dynamic-memory/#comment-11972</link>
		<dc:creator>az első Hyper-v patch kapcs&#225;n</dc:creator>
		<pubDate>Sun, 12 Jun 2011 21:23:39 +0000</pubDate>
		<guid isPermaLink="false">http://www.vcritical.com/?p=2270#comment-11972</guid>
		<description>[...] “A Memory overcommitment potenciálisan veszélyes, éles környezetben nagyon kockázatos” A minap olvastam, hogy mégiscsak lesz Hyper-V 2-ben hasonó feature… Most már nem [...]</description>
		<content:encoded><![CDATA[<p>[...] “A Memory overcommitment potenciálisan veszélyes, éles környezetben nagyon kockázatos” A minap olvastam, hogy mégiscsak lesz Hyper-V 2-ben hasonó feature… Most már nem [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Tweets that mention Post-R2 release of Hyper-V may include memory overcommit - Dynamic Memory &#124; VCritical -- Topsy.com</title>
		<link>http://www.vcritical.com/2010/02/hello-dynamic-memory/#comment-9655</link>
		<dc:creator>Tweets that mention Post-R2 release of Hyper-V may include memory overcommit - Dynamic Memory &#124; VCritical -- Topsy.com</dc:creator>
		<pubDate>Sat, 06 Feb 2010 16:30:27 +0000</pubDate>
		<guid isPermaLink="false">http://www.vcritical.com/?p=2270#comment-9655</guid>
		<description>[...] This post was mentioned on Twitter by Eric Gray, Eric Gray, Eric Gray, William Lam, Andrew Storrs and others. Andrew Storrs said: RT @eric_gray: VCritical: Hello Dynamic Memory? http://bit.ly/91tAAs [...]</description>
		<content:encoded><![CDATA[<p>[...] This post was mentioned on Twitter by Eric Gray, Eric Gray, Eric Gray, William Lam, Andrew Storrs and others. Andrew Storrs said: RT @eric_gray: VCritical: Hello Dynamic Memory? <a href="http://bit.ly/91tAAs" rel="nofollow">http://bit.ly/91tAAs</a> [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Phil</title>
		<link>http://www.vcritical.com/2010/02/hello-dynamic-memory/#comment-9653</link>
		<dc:creator>Phil</dc:creator>
		<pubDate>Fri, 05 Feb 2010 16:56:44 +0000</pubDate>
		<guid isPermaLink="false">http://www.vcritical.com/?p=2270#comment-9653</guid>
		<description>Mark: &quot;That’s where VMware DRS comes in…&quot;

or PROTips in a Hyper-V environment.</description>
		<content:encoded><![CDATA[<p>Mark: &#8220;That’s where VMware DRS comes in…&#8221;</p>
<p>or PROTips in a Hyper-V environment.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Fernando</title>
		<link>http://www.vcritical.com/2010/02/hello-dynamic-memory/#comment-9650</link>
		<dc:creator>Fernando</dc:creator>
		<pubDate>Thu, 04 Feb 2010 10:31:14 +0000</pubDate>
		<guid isPermaLink="false">http://www.vcritical.com/?p=2270#comment-9650</guid>
		<description>Brilliant explanation :-D</description>
		<content:encoded><![CDATA[<p>Brilliant explanation <img src='http://www.vcritical.com/wp-includes/images/smilies/icon_biggrin.gif' alt=':-D' class='wp-smiley' /> </p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Mark Chuang</title>
		<link>http://www.vcritical.com/2010/02/hello-dynamic-memory/#comment-9649</link>
		<dc:creator>Mark Chuang</dc:creator>
		<pubDate>Wed, 03 Feb 2010 20:08:26 +0000</pubDate>
		<guid isPermaLink="false">http://www.vcritical.com/?p=2270#comment-9649</guid>
		<description>@James

It feels like saying that &quot;VMware&#039;s approach can lead to paging&quot; while &quot;MS&#039;s approach won&#039;t&quot; misses the bigger picture.

Let&#039;s look at the scenario that would lead to paging for VMware, i.e. the VMs on a host cumulatively need more memory than exists on the host. In the MS scheme (if I&#039;m interpreting your explanation correctly), the MS balloon driver will try to free up memory, but it won&#039;t be able to because all of the memory is actively being used. So you end up with Hyper-V VMs that need more memory but can&#039;t get it, so the performance for those VMs are essentially capped as well.

So in both approaches, the bigger picture/solution is that you&#039;ll need to move 1 or more VMs to another host (since AFAIK, neither company has figured out how to defy the laws of physics and create more physical memory out of thin air). That&#039;s where VMware DRS comes in...

(Disclosure: Yes, I work for VMware.)</description>
		<content:encoded><![CDATA[<p>@James</p>
<p>It feels like saying that &#8220;VMware&#8217;s approach can lead to paging&#8221; while &#8220;MS&#8217;s approach won&#8217;t&#8221; misses the bigger picture.</p>
<p>Let&#8217;s look at the scenario that would lead to paging for VMware, i.e. the VMs on a host cumulatively need more memory than exists on the host. In the MS scheme (if I&#8217;m interpreting your explanation correctly), the MS balloon driver will try to free up memory, but it won&#8217;t be able to because all of the memory is actively being used. So you end up with Hyper-V VMs that need more memory but can&#8217;t get it, so the performance for those VMs are essentially capped as well.</p>
<p>So in both approaches, the bigger picture/solution is that you&#8217;ll need to move 1 or more VMs to another host (since AFAIK, neither company has figured out how to defy the laws of physics and create more physical memory out of thin air). That&#8217;s where VMware DRS comes in&#8230;</p>
<p>(Disclosure: Yes, I work for VMware.)</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Anton Zhbankov</title>
		<link>http://www.vcritical.com/2010/02/hello-dynamic-memory/#comment-9648</link>
		<dc:creator>Anton Zhbankov</dc:creator>
		<pubDate>Wed, 03 Feb 2010 18:10:29 +0000</pubDate>
		<guid isPermaLink="false">http://www.vcritical.com/?p=2270#comment-9648</guid>
		<description>James, I know how can you give VM more memory - Windows 2003 Enterprise and above support memory hot-add. But how can you hot remove memory?
I see only one way to do this - ballooning = swapping.</description>
		<content:encoded><![CDATA[<p>James, I know how can you give VM more memory &#8211; Windows 2003 Enterprise and above support memory hot-add. But how can you hot remove memory?<br />
I see only one way to do this &#8211; ballooning = swapping.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Anton Zhbankov</title>
		<link>http://www.vcritical.com/2010/02/hello-dynamic-memory/#comment-9647</link>
		<dc:creator>Anton Zhbankov</dc:creator>
		<pubDate>Wed, 03 Feb 2010 18:06:56 +0000</pubDate>
		<guid isPermaLink="false">http://www.vcritical.com/?p=2270#comment-9647</guid>
		<description>It&#039;s dynamic memory! ;)</description>
		<content:encoded><![CDATA[<p>It&#8217;s dynamic memory! <img src='http://www.vcritical.com/wp-includes/images/smilies/icon_wink.gif' alt=';)' class='wp-smiley' /> </p>
]]></content:encoded>
	</item>
	<item>
		<title>By: James O'Neill</title>
		<link>http://www.vcritical.com/2010/02/hello-dynamic-memory/#comment-9646</link>
		<dc:creator>James O'Neill</dc:creator>
		<pubDate>Wed, 03 Feb 2010 17:21:47 +0000</pubDate>
		<guid isPermaLink="false">http://www.vcritical.com/?p=2270#comment-9646</guid>
		<description>Anton, you&#039;re right we will probably see lots of arguments about the correct usage of &quot;commit&quot; and &quot;Overcommit&quot;.  Overcommitment (at least when I was introduced to the term in the context of non-virtualized OSes) is the point where paging begins.

Far be it from me to advise VMware on how to market their products but it would seem to me that the whole upside on page sharing is that it allows (sum of granted) &gt; (memory physical) without actually being overcommitted and needing to page (bad).   

Microsoft&#039;s dynamic memory (as seen in 2008) didn&#039;t page -  so it reduced what was granted to one VM to increase what was granted to another.   Different beasts.</description>
		<content:encoded><![CDATA[<p>Anton, you&#8217;re right we will probably see lots of arguments about the correct usage of &#8220;commit&#8221; and &#8220;Overcommit&#8221;.  Overcommitment (at least when I was introduced to the term in the context of non-virtualized OSes) is the point where paging begins.</p>
<p>Far be it from me to advise VMware on how to market their products but it would seem to me that the whole upside on page sharing is that it allows (sum of granted) &gt; (memory physical) without actually being overcommitted and needing to page (bad).   </p>
<p>Microsoft&#8217;s dynamic memory (as seen in 2008) didn&#8217;t page &#8211;  so it reduced what was granted to one VM to increase what was granted to another.   Different beasts.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Fernando</title>
		<link>http://www.vcritical.com/2010/02/hello-dynamic-memory/#comment-9644</link>
		<dc:creator>Fernando</dc:creator>
		<pubDate>Tue, 02 Feb 2010 22:39:26 +0000</pubDate>
		<guid isPermaLink="false">http://www.vcritical.com/?p=2270#comment-9644</guid>
		<description>So, what is it then ?</description>
		<content:encoded><![CDATA[<p>So, what is it then ?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Anton Zhbankov</title>
		<link>http://www.vcritical.com/2010/02/hello-dynamic-memory/#comment-9638</link>
		<dc:creator>Anton Zhbankov</dc:creator>
		<pubDate>Tue, 02 Feb 2010 16:47:59 +0000</pubDate>
		<guid isPermaLink="false">http://www.vcritical.com/?p=2270#comment-9638</guid>
		<description>James, 
AFAIR VMware defines Memory Overcommitment as (Sum of memory granted) &gt; (Memory physical). So if we have 32GB of memory and 40GB granted to running VMs - memory is overcommited, even if working set is 15GB.

TSP is included to Memory Overcommitment techniques with ballooning. So actually it&#039;s just a question of terms.

Marketing always will find something to say, no matter what engineers do.</description>
		<content:encoded><![CDATA[<p>James,<br />
AFAIR VMware defines Memory Overcommitment as (Sum of memory granted) &gt; (Memory physical). So if we have 32GB of memory and 40GB granted to running VMs &#8211; memory is overcommited, even if working set is 15GB.</p>
<p>TSP is included to Memory Overcommitment techniques with ballooning. So actually it&#8217;s just a question of terms.</p>
<p>Marketing always will find something to say, no matter what engineers do.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

