<?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: Blades and Virtualization Aren&#8217;t Mutually Exclusive: Part Three, IBM Traditional Expansion Options</title>
	<atom:link href="http://blog.scottlowe.org/2009/02/13/blades-and-virtualization-arent-mutually-exclusive-part-three-ibm-traditional-expansion-options/feed/" rel="self" type="application/rss+xml" />
	<link>http://blog.scottlowe.org/2009/02/13/blades-and-virtualization-arent-mutually-exclusive-part-three-ibm-traditional-expansion-options/</link>
	<description>The weblog of an IT pro specializing in virtualization, storage, and servers</description>
	<lastBuildDate>Wed, 08 Feb 2012 17:13:47 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=</generator>
	<item>
		<title>By: Aaron Delp</title>
		<link>http://blog.scottlowe.org/2009/02/13/blades-and-virtualization-arent-mutually-exclusive-part-three-ibm-traditional-expansion-options/comment-page-1/#comment-44371</link>
		<dc:creator>Aaron Delp</dc:creator>
		<pubDate>Mon, 04 May 2009 13:54:38 +0000</pubDate>
		<guid isPermaLink="false">http://blog.scottlowe.org/?p=1176#comment-44371</guid>
		<description>BillH - Thank you as always for the informative comment!</description>
		<content:encoded><![CDATA[<p>BillH &#8211; Thank you as always for the informative comment!</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: BillH</title>
		<link>http://blog.scottlowe.org/2009/02/13/blades-and-virtualization-arent-mutually-exclusive-part-three-ibm-traditional-expansion-options/comment-page-1/#comment-44363</link>
		<dc:creator>BillH</dc:creator>
		<pubDate>Sat, 02 May 2009 17:22:36 +0000</pubDate>
		<guid isPermaLink="false">http://blog.scottlowe.org/?p=1176#comment-44363</guid>
		<description>I couldn&#039;t mention the new blades prior to announce (of course).  You are correct that older servers could not deliver full bandwidth dual-port 10Gb Ethernet over a PCIe x8 bus segment.  (Realistic bandwidth would top out around 13Gbps in each direction, shared across the two ports.)

The full bandwidth of four 10Gb Ethernet ports on each blade does require the newest/fastest chipset.  The HS22 blades have the Nahalem Intel processors, which now support PCI-Express (PCIe) Gen2 I/O.  This provides double the I/O bus speed when a Gen2 device is connected.  (I haven&#039;t seen published numbers yet, but I expect to see well over 25Gb in each direction from a Gen2 x8 PCIe bus segment.)

The 4-port CFFh I/O card uses two dual-port Broadcom 10Gb Ethernet chips.  It is a small hardware detail, but a significant performance benefit, that each of the two chips has its own 8x PCIe bus segment.  This is unique to the IBM BladeCenter CFFh architecture.  Unlike standard PCIe adapters that provide just a single PCIe bus segment.  A standard PCIe adapter would require the addition of a PCIe switch to split the available bandwidth from the server and allow connection of the two Ethernet chips.  The CFFh card can provide a large single PCIe bus (a x16 Gen2 bus segment capable of a datarate somewhere over 50Gbps!) or multiple full PCIe bus segments in various combinations of x8 or x4 PCIe widths, all capable of Gen2 PCIe speed operation - with newer , Gen2 capable adapter cards.  (Of course, PCIe Gen2 is fully backwards compatible with existing PCIe Gen1 devices.  The links autonegotiate to the right speed, without any manual intervention required.)</description>
		<content:encoded><![CDATA[<p>I couldn&#8217;t mention the new blades prior to announce (of course).  You are correct that older servers could not deliver full bandwidth dual-port 10Gb Ethernet over a PCIe x8 bus segment.  (Realistic bandwidth would top out around 13Gbps in each direction, shared across the two ports.)</p>
<p>The full bandwidth of four 10Gb Ethernet ports on each blade does require the newest/fastest chipset.  The HS22 blades have the Nahalem Intel processors, which now support PCI-Express (PCIe) Gen2 I/O.  This provides double the I/O bus speed when a Gen2 device is connected.  (I haven&#8217;t seen published numbers yet, but I expect to see well over 25Gb in each direction from a Gen2 x8 PCIe bus segment.)</p>
<p>The 4-port CFFh I/O card uses two dual-port Broadcom 10Gb Ethernet chips.  It is a small hardware detail, but a significant performance benefit, that each of the two chips has its own 8x PCIe bus segment.  This is unique to the IBM BladeCenter CFFh architecture.  Unlike standard PCIe adapters that provide just a single PCIe bus segment.  A standard PCIe adapter would require the addition of a PCIe switch to split the available bandwidth from the server and allow connection of the two Ethernet chips.  The CFFh card can provide a large single PCIe bus (a x16 Gen2 bus segment capable of a datarate somewhere over 50Gbps!) or multiple full PCIe bus segments in various combinations of x8 or x4 PCIe widths, all capable of Gen2 PCIe speed operation &#8211; with newer , Gen2 capable adapter cards.  (Of course, PCIe Gen2 is fully backwards compatible with existing PCIe Gen1 devices.  The links autonegotiate to the right speed, without any manual intervention required.)</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: adelp</title>
		<link>http://blog.scottlowe.org/2009/02/13/blades-and-virtualization-arent-mutually-exclusive-part-three-ibm-traditional-expansion-options/comment-page-1/#comment-43966</link>
		<dc:creator>adelp</dc:creator>
		<pubDate>Wed, 25 Mar 2009 14:16:53 +0000</pubDate>
		<guid isPermaLink="false">http://blog.scottlowe.org/?p=1176#comment-43966</guid>
		<description>@william bishop - I sent you an e-mail with the statment.  Let me know if you need anything else.

@BillH - Good points all around.  I will correct the article on Bays7-10 for 10G.  I was not aware of the 4x10G solution.  I have questions out to some people in IBM on it because I don&#039;t see how you can push that kind of bandwidth through the chipset.  You can&#039;t do it on a 3850 and still be supported without a SPORE.  I am amazaed that is a supported config but I have been wrong before!

Yes, 8GB is now out so anything FC above can really be 4GB/8GB.

My intention with iSCSI is VMWare.  I should be more clear in the article.  I will correct that.  There is no hardware iSCSI support for the other NICs.  The problem with the current IBM solution is HP now has a card out that fits with everything else and IBM doesn&#039;t.

Thanks again for all the comments!</description>
		<content:encoded><![CDATA[<p>@william bishop &#8211; I sent you an e-mail with the statment.  Let me know if you need anything else.</p>
<p>@BillH &#8211; Good points all around.  I will correct the article on Bays7-10 for 10G.  I was not aware of the 4x10G solution.  I have questions out to some people in IBM on it because I don&#8217;t see how you can push that kind of bandwidth through the chipset.  You can&#8217;t do it on a 3850 and still be supported without a SPORE.  I am amazaed that is a supported config but I have been wrong before!</p>
<p>Yes, 8GB is now out so anything FC above can really be 4GB/8GB.</p>
<p>My intention with iSCSI is VMWare.  I should be more clear in the article.  I will correct that.  There is no hardware iSCSI support for the other NICs.  The problem with the current IBM solution is HP now has a card out that fits with everything else and IBM doesn&#8217;t.</p>
<p>Thanks again for all the comments!</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: BillH</title>
		<link>http://blog.scottlowe.org/2009/02/13/blades-and-virtualization-arent-mutually-exclusive-part-three-ibm-traditional-expansion-options/comment-page-1/#comment-43914</link>
		<dc:creator>BillH</dc:creator>
		<pubDate>Thu, 19 Mar 2009 18:53:18 +0000</pubDate>
		<guid isPermaLink="false">http://blog.scottlowe.org/?p=1176#comment-43914</guid>
		<description>One correction - The 10Gb Ethernet switch only takes one switch slot.  The first one would normally go in Switch Bay 7.  A second 10Gb Ethernet switch module would go into Switch Bay 9.  
http://www-03.ibm.com/systems/bladecenter/hardware/openfabric/ethernet.html

Addition - If you want more connectivity, there is a four port 10Gb CFFh card that can be used with up to four 10Gb Ethernet switches in the chassis.  (this is in addition to the base two 1Gb Ethernet ports, and two ports (FC or Enet) added with a CFFv card.)

Addition - There is recent higher bandwidth &#039;combo&#039; CFFh adapter (dual Gb Ethernet + dual 8Gb FC)

Comment - iSCSI is supported very well with the basic Ethernet NICs, so no iSCSI specific HW adapter option is being offered.</description>
		<content:encoded><![CDATA[<p>One correction &#8211; The 10Gb Ethernet switch only takes one switch slot.  The first one would normally go in Switch Bay 7.  A second 10Gb Ethernet switch module would go into Switch Bay 9.<br />
<a href="http://www-03.ibm.com/systems/bladecenter/hardware/openfabric/ethernet.html" rel="nofollow">http://www-03.ibm.com/systems/bladecenter/hardware/openfabric/ethernet.html</a></p>
<p>Addition &#8211; If you want more connectivity, there is a four port 10Gb CFFh card that can be used with up to four 10Gb Ethernet switches in the chassis.  (this is in addition to the base two 1Gb Ethernet ports, and two ports (FC or Enet) added with a CFFv card.)</p>
<p>Addition &#8211; There is recent higher bandwidth &#8216;combo&#8217; CFFh adapter (dual Gb Ethernet + dual 8Gb FC)</p>
<p>Comment &#8211; iSCSI is supported very well with the basic Ethernet NICs, so no iSCSI specific HW adapter option is being offered.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: william bishop</title>
		<link>http://blog.scottlowe.org/2009/02/13/blades-and-virtualization-arent-mutually-exclusive-part-three-ibm-traditional-expansion-options/comment-page-1/#comment-43872</link>
		<dc:creator>william bishop</dc:creator>
		<pubDate>Sun, 15 Mar 2009 03:24:40 +0000</pubDate>
		<guid isPermaLink="false">http://blog.scottlowe.org/?p=1176#comment-43872</guid>
		<description>Yep, valid.</description>
		<content:encoded><![CDATA[<p>Yep, valid.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: adelp</title>
		<link>http://blog.scottlowe.org/2009/02/13/blades-and-virtualization-arent-mutually-exclusive-part-three-ibm-traditional-expansion-options/comment-page-1/#comment-43842</link>
		<dc:creator>adelp</dc:creator>
		<pubDate>Thu, 12 Mar 2009 18:56:34 +0000</pubDate>
		<guid isPermaLink="false">http://blog.scottlowe.org/?p=1176#comment-43842</guid>
		<description>Net Pro - Thank you very much for the part numbers!!!

William Bishop - I spoke to our Kingston rep and he send me the written statement of the agreement between IBM and Kingston.  It covers all products.  Is your e-mail on the comments valid?  I&#039;d be happy to send you the soft copy.</description>
		<content:encoded><![CDATA[<p>Net Pro &#8211; Thank you very much for the part numbers!!!</p>
<p>William Bishop &#8211; I spoke to our Kingston rep and he send me the written statement of the agreement between IBM and Kingston.  It covers all products.  Is your e-mail on the comments valid?  I&#8217;d be happy to send you the soft copy.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: william bishop</title>
		<link>http://blog.scottlowe.org/2009/02/13/blades-and-virtualization-arent-mutually-exclusive-part-three-ibm-traditional-expansion-options/comment-page-1/#comment-43743</link>
		<dc:creator>william bishop</dc:creator>
		<pubDate>Sun, 01 Mar 2009 14:58:22 +0000</pubDate>
		<guid isPermaLink="false">http://blog.scottlowe.org/?p=1176#comment-43743</guid>
		<description>Aaron, I&#039;m told by an IBM rep that the 8gb kingston memory modules aren&#039;t supported by IBM....Have you got a support sheet on them?</description>
		<content:encoded><![CDATA[<p>Aaron, I&#8217;m told by an IBM rep that the 8gb kingston memory modules aren&#8217;t supported by IBM&#8230;.Have you got a support sheet on them?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Net Pro</title>
		<link>http://blog.scottlowe.org/2009/02/13/blades-and-virtualization-arent-mutually-exclusive-part-three-ibm-traditional-expansion-options/comment-page-1/#comment-43672</link>
		<dc:creator>Net Pro</dc:creator>
		<pubDate>Fri, 20 Feb 2009 15:40:59 +0000</pubDate>
		<guid isPermaLink="false">http://blog.scottlowe.org/?p=1176#comment-43672</guid>
		<description>On our HS21XM blades the FRU for a 15.8 GB SATA drive (SSD) with a transfer speed of 1.5Gb/s is: 43W7609.
The FRU for the &quot;adapter&quot; where the two SSD drives plug into is: 39M4583.
These days IBM offers an SSD drive with double the capacity but rumor has it that it cannot be configured as RAID-1, not sure if it is true.</description>
		<content:encoded><![CDATA[<p>On our HS21XM blades the FRU for a 15.8 GB SATA drive (SSD) with a transfer speed of 1.5Gb/s is: 43W7609.<br />
The FRU for the &#8220;adapter&#8221; where the two SSD drives plug into is: 39M4583.<br />
These days IBM offers an SSD drive with double the capacity but rumor has it that it cannot be configured as RAID-1, not sure if it is true.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: slowe</title>
		<link>http://blog.scottlowe.org/2009/02/13/blades-and-virtualization-arent-mutually-exclusive-part-three-ibm-traditional-expansion-options/comment-page-1/#comment-43650</link>
		<dc:creator>slowe</dc:creator>
		<pubDate>Tue, 17 Feb 2009 15:19:27 +0000</pubDate>
		<guid isPermaLink="false">http://blog.scottlowe.org/?p=1176#comment-43650</guid>
		<description>Aaron gets all the credit for this series...and there is more yet to come!</description>
		<content:encoded><![CDATA[<p>Aaron gets all the credit for this series&#8230;and there is more yet to come!</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: HP BladeSystem Team</title>
		<link>http://blog.scottlowe.org/2009/02/13/blades-and-virtualization-arent-mutually-exclusive-part-three-ibm-traditional-expansion-options/comment-page-1/#comment-43649</link>
		<dc:creator>HP BladeSystem Team</dc:creator>
		<pubDate>Tue, 17 Feb 2009 15:03:57 +0000</pubDate>
		<guid isPermaLink="false">http://blog.scottlowe.org/?p=1176#comment-43649</guid>
		<description>Scott, great write up on I/O expansion for virtualization.  We agree – historically, barriers to virtualization in a bladed environment have been limited connectivity,  high networking costs, fixed network bandwidth and insufficient memory and excessive power use.  We look forward to the rest of this series.</description>
		<content:encoded><![CDATA[<p>Scott, great write up on I/O expansion for virtualization.  We agree – historically, barriers to virtualization in a bladed environment have been limited connectivity,  high networking costs, fixed network bandwidth and insufficient memory and excessive power use.  We look forward to the rest of this series.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

