<?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>Blades Made Simple™ &#187; VMmark</title>
	<atom:link href="http://bladesmadesimple.com/tag/vmmark/feed/" rel="self" type="application/rss+xml" />
	<link>http://bladesmadesimple.com</link>
	<description>Making blade servers simple</description>
	<lastBuildDate>Tue, 15 May 2012 11:18:05 +0000</lastBuildDate>
	<language>en</language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3.1</generator>
		<item>
		<title>Dell M910 Blade Server Achieves #1 VMmark Score</title>
		<link>http://bladesmadesimple.com/2010/08/dell-m910-blade-server-achieves-1-vmmark-score/</link>
		<comments>http://bladesmadesimple.com/2010/08/dell-m910-blade-server-achieves-1-vmmark-score/#comments</comments>
		<pubDate>Fri, 06 Aug 2010 04:01:07 +0000</pubDate>
		<dc:creator>Kevin Houston</dc:creator>
				<category><![CDATA[Dell]]></category>
		<category><![CDATA[VMmark]]></category>
		<category><![CDATA[blade server]]></category>
		<category><![CDATA[Intel Xeon 7500]]></category>
		<category><![CDATA[M910]]></category>
		<category><![CDATA[PowerEdge]]></category>

		<guid isPermaLink="false">http://bladesmadesimple.com/?p=771</guid>
		<description><![CDATA[The VMware VMmark web site was recently updated to show Dell&#8217;s PowerEdge M910 blade server in the #1 slot (for blades) in the 16 core space. I think the PowerEdge M910 is very intriguing, so I thought I&#8217;d spend some time highlighting the features. Before I begin, let me explain what the VMmark testing is about.   VMmark enables equipment manufacturers, software [...]]]></description>
			<content:encoded><![CDATA[
<div class="topsy_widget_data topsy_theme_blue" style="float: right;margin-left: 0.75em; background: url(data:,%7B%20%22url%22%3A%20%22http%253A%252F%252Fbladesmadesimple.com%252F2010%252F08%252Fdell-m910-blade-server-achieves-1-vmmark-score%252F%22%2C%20%22style%22%3A%20%22big%22%2C%20%22title%22%3A%20%22Dell%20M910%20Blade%20Server%20Achieves%20%231%20VMmark%20Score%20%23blade%20server%20%23Dell%20%23Intel%20Xeon%207500%20%23M910%20%23PowerEdge%20%23VMmark%22%20%7D);"></div>
<p><a href="http://bladesmadesimple.com/wp-content/uploads/2010/08/Dell-M910-Blad-front.jpg"><img class="alignleft size-full wp-image-778" style="margin: 2px 4px;" title="Dell M910 Blad - front" src="http://bladesmadesimple.com/wp-content/uploads/2010/08/Dell-M910-Blad-front.jpg" alt="" width="56" height="127" /></a>The VMware VMmark web site was recently updated to show <strong><span style="color: #ff0000;">Dell&#8217;s PowerEdge M910</span></strong> blade server in the #1 slot (for blades) in the 16 core space. I think the PowerEdge M910 is very intriguing, so I thought I&#8217;d spend some time highlighting the features.<span id="more-771"></span> Before I begin, let me explain what the VMmark testing is about.   VMmark enables equipment manufacturers, software vendors, system integrators and other organizations to:</p>
<ul>
<li>Measure virtual machine performance accurately and reliably</li>
<li>Determine the performance of different hardware and virtualization platforms</li>
<li>Make appropriate hardware decisions for your virtual infrastructure</li>
</ul>
<p>VMware developed VMmark as a standard methodology for comparing virtualized systems. According to VMware’s VMmark <a onclick="_gaq.push(['_trackEvent','outbound-article','www.vmware.com']);" href="http://www.vmware.com/products/vmmark/overview.html" target="_blank">website</a>, the benchmark system in VMmark is comprised of a series of “sub-tests” that are derived from commonly used load-generation tools, as well as from benchmarks developed by the Standard Performance Evaluation Corporation (SPEC®). In parallel to VMmark, VMware is a member of the <a onclick="_gaq.push(['_trackEvent','outbound-article','www.spec.org']);" href="http://www.spec.org/specvirtualization/">SPEC Virtualization subcommittee</a> and is working with other SPEC members to create the next generation virtualization benchmark.</p>
<p>In testing the terms, a “tile” is simply a collection of virtual machines (VM’s) that are executing a set of diverse workloads designed to represent a natural work environment.   The total number of tiles that a server can handle provides a detailed measurement of that server’s consolidation capacity.  The more tiles, the better.  The faster the performance, the better.</p>
<p><strong><span style="color: #0000ff;">Top 3 VMmark Results for 16 Core Blade Servers (as of 8/5/2010)</span></strong><em><span style="color: #0000ff;">…</span>click on the link to open the details</em></p>
<p> #1 &#8211; <strong>Dell PowerEdge M910</strong> (<em>2 Sockets, 16 cores;  Intel Xeon X7560 CPU</em>) running VMware ESX v4.0 –<a href="http://www.vmware.com/files/pdf/vmmark/VMmark-Dell-2010-07-13-M910-BLM.pdf" target="_blank"><strong>37.11@26 tiles </strong></a>(published 7/13/2010)</p>
<p>#2 &#8211; <strong>Dell PowerEdge M905</strong> (4 Sockets, <em>16 cores;  AMD Opteron 8393 SE</em>) running VMware ESX v4.0 – <strong><a onclick="_gaq.push(['_trackEvent','outbound-article','www.vmware.com']);" href="http://www.vmware.com/files/pdf/vmmark/VMmark-Dell-2009-06-18-M905.pdf" target="_blank">22.90@17 tiles</a></strong> (published 6/19/2009)</p>
<p>#3 &#8211; <strong>HP ProLiant BL685 G6</strong> (<em>Four Core AMD Opteron 8389</em>) running VMware ESX v4.0 – <strong><a onclick="_gaq.push(['_trackEvent','outbound-article','www.vmware.com']);" href="http://www.vmware.com/files/pdf/vmmark/VMmark-HP-2009-04-24-BL685G6.pdf" target="_blank">20.87@14 tiles</a></strong> (published 4/24/2009)</p>
<div class="mceTemp"><span style="color: #0000ff;"><strong>About the Dell PowerEdge M910 Blade Server</strong><br />
</span>Some details about the server:</div>
<ul>
<li>uses Intel Xeon 7500 or 6500 CPUs</li>
<li>has support for up to 512GB using 32 x 16 DIMMs</li>
<li>comes 4 Ethernet ports via two embedded Broadcom NetExtreme II Dual Port 5709S Gigabit Ethernet NICs with failover and load balancing.</li>
<li>has two 2.5″ Hot-Swappable SAS/Solid State Drives</li>
<li><strong>4</strong> available I/O mezzanine card slots</li>
<li>comes with a Matrox G200eW w/ 8MB memory standard</li>
<li>can function on <strong>2 CPUs with access to all 32 DIMM slots</strong></li>
</ul>
<p><strong><a href="http://bladesmadesimple.com/wp-content/uploads/2010/08/Overview-of-M910.jpg"><img class="size-full wp-image-780 alignleft" title="Overview of M910" src="http://bladesmadesimple.com/wp-content/uploads/2010/08/Overview-of-M910.jpg" alt="" width="576" height="432" /></a></strong></p>
<div class="mceTemp"> </div>
<div class="mceTemp">One important note is that Dell has 4 I/O mezzanine cards.  This is very important to understand, so let&#8217;s take a look at the Dell M1000e Chassis&#8217; I/O Mapping.</div>
<div class="mceTemp"><strong> <a href="http://bladesmadesimple.com/wp-content/uploads/2010/08/Dell-M1000-I-O-Mapping-rev-8-5-10.jpg"><img class="alignleft size-full wp-image-783" title="Dell M1000e I-O Mapping rev 8-5-10" src="http://bladesmadesimple.com/wp-content/uploads/2010/08/Dell-M1000-I-O-Mapping-rev-8-5-10.jpg" alt="Dell M1000e I-O Mapping" width="563" height="274" /></a></strong></div>
<div class="mceTemp"> </div>
<div class="mceTemp">YES &#8211; this looks complex, but it&#8217;s not.  Here&#8217;s the breakdown by I/O Bay Module.  For the record, I have them labeled as &#8220;I/O Bay 1 &#8211; 6&#8243; however Dell uses &#8220;A1, A2, B1, B2 and C1, C2&#8243;.  They are the same &#8211; I just listed them numerically to make it easier to follow.</div>
<div class="mceTemp"><strong><span style="color: #0000ff;">I/O Bays 1 and 2</span></strong> <br />
These I/O Bays are connected to the on-board Ethernet.  In the case of the M910, there are 4 Ethernet ports.</div>
<div class="mceTemp"><a href="http://bladesmadesimple.com/wp-content/uploads/2010/08/Dell-M1000-I-O-Bay-1-and-2.jpg"><img class="alignleft size-full wp-image-784" title="Dell M1000e I-O Bay 1 and 2" src="http://bladesmadesimple.com/wp-content/uploads/2010/08/Dell-M1000-I-O-Bay-1-and-2.jpg" alt="Dell M1000e I-O Bay 1 and 2" width="563" height="282" /></a></div>
<div class="mceTemp"> </div>
<div class="mceTemp"><strong> </strong></div>
<div class="mceTemp"><span style="color: #0000ff;"><strong>I/O Bays 3 and 4</strong> <br />
</span>These I/O Bays are connected to Mezzanine Card Slots 1 and 3.  These can provide 4 ports per card if a QUAD port card is used &#8211; otherwise, only two ports would be used.</div>
<div class="mceTemp"><a href="http://bladesmadesimple.com/wp-content/uploads/2010/08/Dell-M1000-I-O-Bay-3-and-4.jpg"><img class="alignleft size-full wp-image-785" title="Dell M1000e I-O Bay 3 and 4" src="http://bladesmadesimple.com/wp-content/uploads/2010/08/Dell-M1000-I-O-Bay-3-and-4.jpg" alt="Dell M1000e I-O Bay 3 and 4" width="591" height="296" /></a></div>
<div class="mceTemp"><strong> </strong></div>
<div class="mceTemp"><strong><span style="color: #0000ff;">I/O Bays 5 and 6</span></strong></div>
<div class="mceTemp">These I/O Bays are connected to Mezzanine Card Slots 2 and 4.  These can provide 4 ports per card if a QUAD port card is used &#8211; otherwise, only two ports would be used.</div>
<div class="mceTemp"><a href="http://bladesmadesimple.com/wp-content/uploads/2010/08/Dell-M1000-I-O-Bay-5-and-6.jpg"><img class="alignleft size-full wp-image-786" title="Dell M1000e I-O Bay 5 and 6" src="http://bladesmadesimple.com/wp-content/uploads/2010/08/Dell-M1000-I-O-Bay-5-and-6.jpg" alt="Dell M1000e I-O Bay 5 and 6" width="563" height="282" /></a></div>
<div class="mceTemp">From the design of the Dell M1000e Chassis, you can see that Dell&#8217;s M910 offers:</div>
<div class="mceTemp">a) physically redundant card connections</div>
<div class="mceTemp">b) Up to 20 ports of I/O</div>
<div class="mceTemp">Let me give an real-world example of how Dell&#8217;s blade architecture can be very exciting.  Imagine you have a need for 12 Ethernet Adapters and 2 Fibre HBAs, however you want to have <strong>redundant, physical </strong>fibre HBAs.  You can do this with the M910 blade server:</div>
<div class="mceTemp">4 Ethernet Ports on the motherboard</div>
<div class="mceTemp">+ 4 Ethernet NICs (via a Quad Port Ethernet Adapter) on Mezzanine card 1</div>
<div class="mceTemp">+ 2 Fibre HBA ports on Mezzanine card 2</div>
<div class="mceTemp">+ 4 Ethernet NICs (via a Quad Port Ethernet Adapter) on Mezzanine card 3</div>
<div class="mceTemp">+ 2 Fibre HBA ports on Mezzanine card 2</div>
<div class="mceTemp"><strong><span style="color: #ff0000;">= 12 Ethernet Ports and 4 Fibre Ports (redundant)</span></strong></div>
<div class="mceTemp"><strong><span style="color: #ff0000;"> </span></strong></div>
<div class="mceTemp"><span style="color: #000000;">In fact &#8211; if you didn&#8217;t need the Fibre HBAs, you could put in 2 x Quad port Ethernet cards and have ANOTHER 8 Ethernet ports (total of 20)!  This is remarkable!  No more physical I/O port limitations, you can achieve the quantity of I/O ports you need without moving to 10Gb.</span></div>
<div class="mceTemp"><span style="color: #000000;"> </span></div>
<div class="mceTemp"><span style="color: #000000;"><strong><span style="color: #0000ff;">FlexMem Bridge Technology Allows for More Memory in 2 Sockets</span></strong></span></div>
<div class="mceTemp"><span style="color: #000000;">Intel&#8217;s Xeon 7500 architecture requires that you have a processor to access the associated memory DIMMs.  However, Dell created an innovative design that allows for you to use the memory associated with a 3rd and 4th processor <span style="text-decoration: underline;">without</span> the need for the processors.  This technology is called &#8220;<strong><span style="color: #ff0000;">FlexMem Bridge</span></strong>.&#8221;  Dell’s FlexMem Bridge technology allows for you to sits in CPU sockets #3 and #4 and connects a memory controller from CPU 1 to the memory DIMMs associated to CPU socket #3 and CPU 2 to the memory associated to CPU Socket #4.   The FlexMem Bridge does two things:</span><strong> </strong></div>
<div class="mceTemp">
<ol>
<li>It extends the Scalable Memory Interconnects (SMI) from CPU 1 and CPU 2 to the memory subsystem of CPU 3 and CPU 4.</li>
<li>It reroutes and terminates the 2nd Quick Path Interconnect (QPI) inter-processor communications links to provide optimal performance which would otherwise be disconnected in a 2 CPU configuration.</li>
</ol>
</div>
<p class="mceTemp">Sometimes it’s easier to view pictures than read descriptions, so take a look at the picture below for a diagram on how this works.<span style="color: #000000;"><a href="http://bladesmadesimple.com/wp-content/uploads/2010/05/FlexMem-Bridge-rev.png"><img class="alignleft size-full wp-image-568" title="FlexMem Bridge (rev)" src="http://bladesmadesimple.com/wp-content/uploads/2010/05/FlexMem-Bridge-rev.png" alt="" width="576" height="321" /></a></span></p>
<p> </p>
<div class="mceTemp">I wrote a post on this technology a few weeks back, so jump over to <a href="http://bladesmadesimple.com/2010/05/dell-flexmem-bridge-helps-save-50-on-virtualization-licensing/" target="_blank">this page</a> and take a look (read the comments &#8211; good discussions were had.)</div>
<p>So &#8211; that about covers it. </p>
<p>For more information on the Dell PowerEdge M910, check out the PowerEdge M910 Product Site at<br />
<a href="http://www.dell.com/us/en/enterprise/servers/poweredge-m910/pd.aspx?refid=poweredge-m910&amp;s=biz&amp;cs=555">http://www.dell.com/us/en/enterprise/servers/poweredge-m910/pd.aspx?refid=poweredge-m910&amp;s=biz&amp;cs=555</a></p>

]]></content:encoded>
			<wfw:commentRss>http://bladesmadesimple.com/2010/08/dell-m910-blade-server-achieves-1-vmmark-score/feed/</wfw:commentRss>
		<slash:comments>15</slash:comments>
		</item>
		<item>
		<title>(UPDATED) Best Blade Server for VMware Is&#8230;</title>
		<link>http://bladesmadesimple.com/2010/06/best-blade-server-for-vmware-is/</link>
		<comments>http://bladesmadesimple.com/2010/06/best-blade-server-for-vmware-is/#comments</comments>
		<pubDate>Thu, 03 Jun 2010 04:01:26 +0000</pubDate>
		<dc:creator>Kevin Houston</dc:creator>
				<category><![CDATA[Cisco]]></category>
		<category><![CDATA[Dell]]></category>
		<category><![CDATA[HP]]></category>
		<category><![CDATA[VMmark]]></category>
		<category><![CDATA[VMware]]></category>
		<category><![CDATA[blade server]]></category>
		<category><![CDATA[Cisco MDS 9134]]></category>
		<category><![CDATA[Cisco UCS B250 M2]]></category>
		<category><![CDATA[Cisco UCS VIC M81KR]]></category>
		<category><![CDATA[Dell PowerEdge M905]]></category>
		<category><![CDATA[EMC CX4-240]]></category>
		<category><![CDATA[Fujitsu BX922 S2]]></category>
		<category><![CDATA[HP ProLiant BL680c G5]]></category>
		<category><![CDATA[HP ProLiant BL685c G6]]></category>

		<guid isPermaLink="false">http://bladesmadesimple.com/?p=599</guid>
		<description><![CDATA[(Updated to include links to results) I&#8217;ve had a few questions lately about &#8220;the best&#8221; blade server to use for virtualization &#8211; specifically VMware virtualization. While the obvious answer is &#8220;it depends&#8221;, I thought it would be an interesting approach to identify the blade servers that ranked in the top 5 in VMware&#8217;s VMmark benchmark.  [...]]]></description>
			<content:encoded><![CDATA[
<div class="topsy_widget_data topsy_theme_blue" style="float: right;margin-left: 0.75em; background: url(data:,%7B%20%22url%22%3A%20%22http%253A%252F%252Fbladesmadesimple.com%252F2010%252F06%252Fbest-blade-server-for-vmware-is%252F%22%2C%20%22style%22%3A%20%22big%22%2C%20%22title%22%3A%20%22%28UPDATED%29%20Best%20Blade%20Server%20for%20VMware%20Is...%20%23blade%20server%20%23Cisco%20MDS%209134%20%23Cisco%20UCS%20B250%20M2%20%23Cisco%20UCS%20VIC%20M81KR%20%23Dell%20PowerEdge%20M905%20%23EMC%20CX4-240%20%23Fujitsu%20BX922%20S2%20%23HP%20ProLiant%20BL680c%20G5%20%23HP%20ProLiant%20BL685c%20G6%20%23VMmark%20%23VMware%22%20%7D);"></div>
<p><em><span style="color: #ff0000;">(Updated to include links to results)</span></em></p>
<p>I&#8217;ve had a few questions lately about &#8220;the best&#8221; blade server to use for virtualization &#8211; specifically <span style="color: #ff0000;"><strong>VMware</strong> </span>virtualization. While the obvious answer is &#8220;it depends&#8221;, I thought it would be an interesting approach to identify the blade servers that ranked in the top 5 in VMware&#8217;s <strong><span style="color: #ff0000;">VMmark</span></strong> benchmark.  Before I begin, let me explain what the VMmark testing is about.   <span id="more-599"></span>VMmark enables equipment manufacturers, software vendors, system integrators and other organizations to:</p>
<ul>
<li>Measure virtual machine performance accurately and reliably</li>
<li>Determine the performance of different hardware and virtualization platforms</li>
<li>Make appropriate hardware decisions for your virtual infrastructure</li>
</ul>
<p>VMware developed VMmark as a standard methodology for comparing virtualized systems. According to VMware&#8217;s VMmark <a href="http://www.vmware.com/products/vmmark/overview.html" target="_blank">website</a>, the benchmark system in VMmark is comprised of a series of “sub-tests” that are derived from commonly used load-generation tools, as well as from benchmarks developed by the Standard Performance Evaluation Corporation (SPEC®). In parallel to VMmark, VMware is a member of the <a href="http://www.spec.org/specvirtualization/">SPEC Virtualization subcommittee</a> and is working with other SPEC members to create the next generation virtualization benchmark.</p>
<p>In testing the terms, a &#8220;tile&#8221; is simply a collection of virtual machines (VM’s) that are executing a set of diverse workloads designed to represent a natural work environment.   The total number of tiles that a server can handle provides a detailed measurement of that server’s consolidation capacity.  The more tiles, the better.  The faster the performance, the better.</p>
<p><span style="color: #0000ff;"><strong>THE RESULTS (as of 6/2/2010)</strong><span style="color: #000000;"><em>&#8230;click on the link to open the details</em></span></span></p>
<p><span style="text-decoration: underline;">24 Cores (4 Sockets)<br />
</span><strong>HP ProLiant BL685c G6</strong> (<em><span style="color: #008000;">Six Core AMD Opteron 8435</span></em>) running VMware ESX v4.0 &#8211; <strong><a href="http://www.vmware.com/files/pdf/vmmark/VMmark-HP-2009-07-14-bl685cg6.pdf" target="_blank">29.19@20 tiles </a></strong>(published 7/14/2009)<br />
<strong>HP ProLiant BL680c G5</strong> (<em><span style="color: #008000;">Six Core Intel Xeon E7458</span></em>) running VMware ESX v3.5.0 Update 3 - <strong><a href="http://www.vmware.com/files/pdf/vmmark/VMmark-HP-2009-03-30-bl680cG5.pdf" target="_blank">18.64@14 tiles</a> </strong>(published 3/30/2009)</p>
<p><span style="text-decoration: underline;">16 Cores (4 Sockets)</span><br />
<strong>Dell PowerEdge M905</strong> (<em><span style="color: #008000;">Four Core AMD Opteron 8393 SE</span></em>) running VMware ESX v4.0 &#8211; <strong><a href="http://www.vmware.com/files/pdf/vmmark/VMmark-Dell-2009-06-18-M905.pdf" target="_blank">22.90@17 tiles</a></strong> (published 6/19/2009)<br />
<strong>HP ProLiant BL685 G6</strong> (<em><span style="color: #008000;">Four Core AMD Opteron 8389</span></em>) running VMware ESX v4.0 &#8211; <strong><a href="http://www.vmware.com/files/pdf/vmmark/VMmark-HP-2009-04-24-BL685G6.pdf" target="_blank">20.87@14 tiles</a></strong> (published 4/24/2009)</p>
<p><span style="text-decoration: underline;">12 Cores (2 Sockets)<br />
</span><strong>Cisco UCS B250 M2</strong> (<em><span style="color: #008000;">Six Core Intel Xeon X5680</span></em>) running VMware ESX v4.0 Update 1 &#8211; <strong><a href="http://www.vmware.com/files/pdf/vmmark/VMmark-Cisco-2010-04-06-UCS-B250-M2.pdf" target="_blank">35.83@26 tiles</a></strong> (published 4/6/2010)<br />
<strong>Fujitsu BX922 S2</strong> (<em><span style="color: #008000;">Six Core Intel Xeon X5680</span></em>) running VMware ESX v4.0 Update 1 &#8211; <strong><a href="http://www.vmware.com/files/pdf/vmmark/VMmark-Fujitsu-2010-04-06-BX922S2.pdf" target="_blank">32.89@24 tiles</a></strong> (published 4/6/2010)</p>
<p><span style="text-decoration: underline;">8 Cores (2 Sockets)</span><br />
<strong>Fujitsu BX922 S2</strong> (<em><span style="color: #008000;">Four Core Intel Xeon X5677</span></em>) running VMware ESX v4.0 Update 1 &#8211; <strong><a href="http://www.vmware.com/files/pdf/vmmark/VMmark-Fujitsu-2010-05-04-BX922S2.pdf" target="_blank">27.99@18tiles</a></strong>(published 5/10/2010)<br />
<strong>HP ProLiant BL490c G6</strong> (<em><span style="color: #008000;">Four Core Intel Xeon X5570</span></em>) runningVMware ESX v4.0 &#8211; <strong><a href="http://www.vmware.com/files/pdf/vmmark/VMmark-HP-2010-04-20-BL490cG6.pdf" target="_blank">25.27@17tiles</a></strong> (published 4/20/2010)</p>
<p><strong><span style="color: #0000ff;">THE WINNER IS&#8230;</span><br />
<span style="color: #ff0000;">Cisco UCS B250 M2</span></strong> running VMware ESX v4.0 Update 1 &#8211; <span style="color: #ff0000;"><strong>35.83 with 26 tiles</strong><br />
</span></p>
<p><strong><span style="color: #339966;">Cisco’s Winning Configuration</span><br />
</strong>So – how did Cisco reach the top server spot?  Here’s the configuration:</p>
<p><em>server config:</em></p>
<ul>
<li>2 x Intel Xeon X5680 Processors</li>
<li>192GB of RAM (48 x 4GB)</li>
<li>1 x Converged Network Adapter (Cisco UCS VIC M81KR)</li>
</ul>
<p>storage config:</p>
<ul>
<li>EMC CX4-240</li>
<li>Cisco MDS 9134</li>
<li>1173.48GB Used Disk Space</li>
<li>1024MB Array Cache</li>
<li>50 disks used on 5 enclosures/shelves (1 with 14 disk, 4 with 9 disks)</li>
<li>55 LUNs used<br />
*21 at 38GB (file server + mail server) over 20 x 73GB SSDs<br />
*5 at 38GB (file server + mail server) over 20 x 73GB SSDs<br />
*21 at 15GB (database) + 2 LUNs at 400GB (Standby, Webserver, Javaserver) over 16 x 450GB 15k disks<br />
*5 at 15GB (database)  over 16 x 450GB 15k disks<br />
* 1 LUN at 20GB (boot) over 5 x 300GB 15k disks</li>
<li>RAID 0 for VMs, RAID 5 for VMware ESX 4.0 O/S</li>
</ul>
<p>As you can see from the information above, the Cisco UCS B250 M2 is the clear winner above all of the blade server offerings.  As you can see, none of the Xeon 7500 blade servers have yet to be tested but when they do, I&#8217;ll be sure to let you know.</p>

]]></content:encoded>
			<wfw:commentRss>http://bladesmadesimple.com/2010/06/best-blade-server-for-vmware-is/feed/</wfw:commentRss>
		<slash:comments>38</slash:comments>
		</item>
		<item>
		<title>Cisco Takes Top 8 Core VMware VMmark Server Position</title>
		<link>http://bladesmadesimple.com/2010/02/cisco-takes-top-8-core-vmware-vmmark-server-position/</link>
		<comments>http://bladesmadesimple.com/2010/02/cisco-takes-top-8-core-vmware-vmmark-server-position/#comments</comments>
		<pubDate>Fri, 05 Feb 2010 16:49:39 +0000</pubDate>
		<dc:creator>Kevin Houston</dc:creator>
				<category><![CDATA[Cisco]]></category>
		<category><![CDATA[HP]]></category>
		<category><![CDATA[VMware]]></category>
		<category><![CDATA[B200]]></category>
		<category><![CDATA[BL490]]></category>
		<category><![CDATA[blade server]]></category>
		<category><![CDATA[EMC]]></category>
		<category><![CDATA[VMmark]]></category>

		<guid isPermaLink="false">http://bladesmadesimple.com/?p=241</guid>
		<description><![CDATA[Cisco is getting some (more) recognition with their UCS blade server product, as they recently achieved the top position for &#8220;8 Core Server&#8221; on VMware&#8217;s VMmark benchmark tool.  VMmark is the industry&#8217;s first (and only credible) virtualization benchmark for x86-based computers.  According to the VMmark website, the Cisco UCS B200 blade server reached a score of 25.06 @ [...]]]></description>
			<content:encoded><![CDATA[
<div class="topsy_widget_data topsy_theme_blue" style="float: right;margin-left: 0.75em; background: url(data:,%7B%20%22url%22%3A%20%22http%253A%252F%252Fbladesmadesimple.com%252F2010%252F02%252Fcisco-takes-top-8-core-vmware-vmmark-server-position%252F%22%2C%20%22style%22%3A%20%22big%22%2C%20%22title%22%3A%20%22Cisco%20Takes%20Top%208%20Core%20VMware%20VMmark%20Server%20Position%20%23B200%20%23BL490%20%23blade%20server%20%23Cisco%20%23EMC%20%23HP%20%23VMmark%20%23VMware%22%20%7D);"></div>
<p>Cisco is getting some (more) recognition with their UCS blade server product, as they recently achieved the top position for &#8220;8 Core Server&#8221; on <a href="http://www.vmware.com/products/vmmark/results.html" target="_blank">VMware&#8217;s VMmark</a> benchmark tool.  VMmark is the industry&#8217;s first (and only credible) virtualization benchmark for x86-based computers.  According to the VMmark website, the Cisco <span style="color: #ff0000;"><strong><a href="http://www.cisco.com/en/US/products/ps10280/index.html" target="_blank">UCS B200</a></strong></span> blade server reached a score of <strong><span style="color: #ff0000;">25.06</span></strong> @ 17 tiles.  A &#8220;tile&#8221; is simple a collection of virtual machines (VM&#8217;s) that are executing a set of diverse workloads designed to represent a natural work environment.   The total number of tiles that a server can handle provides a detailed measurement of that server&#8217;s consolidation capacity.</p>
<p><strong>Cisco&#8217;s Winning Configuration<br />
</strong>So &#8211; how did Cisco reach the top server spot?  Here&#8217;s the configuration:</p>
<p><span style="text-decoration: underline;"><em>server config:</em></span></p>
<ul>
<li>2 x Intel Xeon X5570 Processors</li>
<li>96GB of RAM (16 x 8GB)</li>
<li>1 x Converged Network Adapter (Cisco UCS M71KR-Q)</li>
</ul>
<p><span style="text-decoration: underline;">storage config:</span></p>
<ul>
<li><span style="color: #ff0000;"><strong>EMC</strong> </span>CX4-240</li>
<li>Cisco MDS 9130</li>
<li>1154.27GB Used Disk Space</li>
<li>1024MB Array Cache</li>
<li>41 disks used on 4 enclosures/shelves (1 with 14 disk, 3 with 9 disks)</li>
<li>37 LUNs used<br />
*17 at 38GB (file server + mail server) over 20 x 73GB SSDs<br />
*17 at 15GB (database) + 2 LUNs at 400GB (Misc) over 16 x 450GB 15k disks<br />
* 1 LUN at 20GB (boot) over 5 x 300GB 15k disks</li>
<li>RAID 0 for VMs, RAID 5 for VMware ESX 4.0 O/S</li>
</ul>
<p>While first place on the <a href="http://www.vmware.com/products/vmmark/results.html" target="_blank">VMmark page (8 cores)</a> shows Fujitsu&#8217;s RX300, it&#8217;s important to note that it was reached using Intel&#8217;s W5590 processor &#8211; a processor that is designed for &#8220;workstations&#8221; &#8211; not servers.  Second place, of server processors, currently shows HP&#8217;s <strong><a href="http://h10010.www1.hp.com/wwpc/us/en/sm/WF25a/3709945-3709945-3328410-241641-3328419-3884113.html" target="_blank"><span style="color: #ff0000;">BL490</span> </a></strong>with <strong><span style="color: #ff0000;">24.54</span></strong> (@ 17 tiles)</p>
<p><em>Thanks to Omar Sultan (@omarsultan) for Tweeting about this and to Harris Sussman for </em><a href="http://blogs.cisco.com/datacenter/comments/vmwaresvmmark_benchmark_position_1_for_ucs_on_intel_xeon_processor_for_8_co/" target="_blank"><em>blogging </em></a><em>about it.</em></p>

]]></content:encoded>
			<wfw:commentRss>http://bladesmadesimple.com/2010/02/cisco-takes-top-8-core-vmware-vmmark-server-position/feed/</wfw:commentRss>
		<slash:comments>11</slash:comments>
		</item>
	</channel>
</rss>

