<?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: New VMware KB &#8211; zeroedthick or eagerzeroedthick</title>
	<atom:link href="http://www.2vcps.com/2010/01/19/new-vmware-kb-zeroedthick-or-eagerzeroedthick/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.2vcps.com/2010/01/19/new-vmware-kb-zeroedthick-or-eagerzeroedthick/</link>
	<description></description>
	<lastBuildDate>Tue, 13 Jul 2010 14:26:09 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.0</generator>
<xhtml:meta xmlns:xhtml="http://www.w3.org/1999/xhtml" name="robots" content="noindex" />
	<item>
		<title>By: Jon Owings</title>
		<link>http://www.2vcps.com/2010/01/19/new-vmware-kb-zeroedthick-or-eagerzeroedthick/comment-page-1/#comment-115</link>
		<dc:creator>Jon Owings</dc:creator>
		<pubDate>Tue, 19 Jan 2010 16:35:43 +0000</pubDate>
		<guid isPermaLink="false">http://www.2vcps.com/?p=267#comment-115</guid>
		<description>Yeah, that comment about recovering the zeroes was my imagination. Storage vendors: start working on that now. You can send the royalties straight to me.

&lt;strong&gt;UPDATE: 3par InForm OS 2.3.1 supports Zero detection and can reclaim the 0&#039;s to keep disks thin. This is done by a special ASIC therefore keeping performance impact at near nothing.&lt;/strong&gt;</description>
		<content:encoded><![CDATA[<p>Yeah, that comment about recovering the zeroes was my imagination. Storage vendors: start working on that now. You can send the royalties straight to me.</p>
<p><strong>UPDATE: 3par InForm OS 2.3.1 supports Zero detection and can reclaim the 0&#8242;s to keep disks thin. This is done by a special ASIC therefore keeping performance impact at near nothing.</strong></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Jon Owings</title>
		<link>http://www.2vcps.com/2010/01/19/new-vmware-kb-zeroedthick-or-eagerzeroedthick/comment-page-1/#comment-114</link>
		<dc:creator>Jon Owings</dc:creator>
		<pubDate>Tue, 19 Jan 2010 16:01:20 +0000</pubDate>
		<guid isPermaLink="false">http://www.2vcps.com/?p=267#comment-114</guid>
		<description>It is very important to consider especially if you are depending on thin provisioning on the SAN. I do believe some Sans like 3par recover the 0&#039;s but I need to double check.

I have never visibly seen too bad of a performance hit using just zerothick. I always would rather plan ahead to avoid follow up calls ( I do professional service installs) related to slowness. 

Another note: It will be slow to deploy a big eagerzeroedthick disk if it is very big.</description>
		<content:encoded><![CDATA[<p>It is very important to consider especially if you are depending on thin provisioning on the SAN. I do believe some Sans like 3par recover the 0&#8242;s but I need to double check.</p>
<p>I have never visibly seen too bad of a performance hit using just zerothick. I always would rather plan ahead to avoid follow up calls ( I do professional service installs) related to slowness. </p>
<p>Another note: It will be slow to deploy a big eagerzeroedthick disk if it is very big.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: wjpatton</title>
		<link>http://www.2vcps.com/2010/01/19/new-vmware-kb-zeroedthick-or-eagerzeroedthick/comment-page-1/#comment-113</link>
		<dc:creator>wjpatton</dc:creator>
		<pubDate>Tue, 19 Jan 2010 15:42:26 +0000</pubDate>
		<guid isPermaLink="false">http://www.2vcps.com/?p=267#comment-113</guid>
		<description>Jon,

I agree that eagerzerothick is great for high I/O VMs, it should be carefully considered as systems that Thin Provision like NFS or V-Max (and many others) will allocate all space once the vmdk is eagerzero.  

zerothick continues to play nice with these technologies, but you do pay some I/O penalty for the thin provisioning which continues to be less and less with each VMFS revision.

In our testing, we saw marginal benefits (1-4% performance) from eagerzero over zero running SQL loads.  We do have a very large EMC V-Max SAN however to cover some of this I/O.  We now only use eagerzero for MSCS VMs.

Good post, and small option many people miss or just overlook!</description>
		<content:encoded><![CDATA[<p>Jon,</p>
<p>I agree that eagerzerothick is great for high I/O VMs, it should be carefully considered as systems that Thin Provision like NFS or V-Max (and many others) will allocate all space once the vmdk is eagerzero.  </p>
<p>zerothick continues to play nice with these technologies, but you do pay some I/O penalty for the thin provisioning which continues to be less and less with each VMFS revision.</p>
<p>In our testing, we saw marginal benefits (1-4% performance) from eagerzero over zero running SQL loads.  We do have a very large EMC V-Max SAN however to cover some of this I/O.  We now only use eagerzero for MSCS VMs.</p>
<p>Good post, and small option many people miss or just overlook!</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Jon Owings</title>
		<link>http://www.2vcps.com/2010/01/19/new-vmware-kb-zeroedthick-or-eagerzeroedthick/comment-page-1/#comment-112</link>
		<dc:creator>Jon Owings</dc:creator>
		<pubDate>Tue, 19 Jan 2010 15:40:37 +0000</pubDate>
		<guid isPermaLink="false">http://www.2vcps.com/?p=267#comment-112</guid>
		<description>oops! Link to the white paper is working now.</description>
		<content:encoded><![CDATA[<p>oops! Link to the white paper is working now.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Jim Peluso</title>
		<link>http://www.2vcps.com/2010/01/19/new-vmware-kb-zeroedthick-or-eagerzeroedthick/comment-page-1/#comment-111</link>
		<dc:creator>Jim Peluso</dc:creator>
		<pubDate>Tue, 19 Jan 2010 15:24:03 +0000</pubDate>
		<guid isPermaLink="false">http://www.2vcps.com/?p=267#comment-111</guid>
		<description>Hey Jon,

Great suggestion. Your link to the white paper isn&#039;t working.  I&#039;d be interested to read the reasoning behind the FT performance increase for high IO VMs.</description>
		<content:encoded><![CDATA[<p>Hey Jon,</p>
<p>Great suggestion. Your link to the white paper isn&#8217;t working.  I&#8217;d be interested to read the reasoning behind the FT performance increase for high IO VMs.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Tweets that mention 2vcps and a Truck » New VMware KB – zeroedthick or eagerzeroedthick -- Topsy.com</title>
		<link>http://www.2vcps.com/2010/01/19/new-vmware-kb-zeroedthick-or-eagerzeroedthick/comment-page-1/#comment-110</link>
		<dc:creator>Tweets that mention 2vcps and a Truck » New VMware KB – zeroedthick or eagerzeroedthick -- Topsy.com</dc:creator>
		<pubDate>Tue, 19 Jan 2010 14:58:02 +0000</pubDate>
		<guid isPermaLink="false">http://www.2vcps.com/?p=267#comment-110</guid>
		<description>[...] This post was mentioned on Twitter by tscalzott, Jon Owings. Jon Owings said: New blog post: New VMware KB - zeroedthick or eagerzeroedthick http://bit.ly/6ZW92l [...]</description>
		<content:encoded><![CDATA[<p>[...] This post was mentioned on Twitter by tscalzott, Jon Owings. Jon Owings said: New blog post: New VMware KB &#8211; zeroedthick or eagerzeroedthick <a href="http://bit.ly/6ZW92l" rel="nofollow">http://bit.ly/6ZW92l</a> [...]</p>
]]></content:encoded>
	</item>
</channel>
</rss>
