<?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: Google&#8217;s Secret 10GbE Switch</title>
	<atom:link href="http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/</link>
	<description>More Signal. Less Noise.</description>
	<lastBuildDate>Thu, 02 Apr 2009 12:29:57 -0700</lastBuildDate>
	<generator>http://wordpress.org/?v=2.9.1</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: De-centralized utilities and the case against Red Shift</title>
		<link>http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1642</link>
		<dc:creator>De-centralized utilities and the case against Red Shift</dc:creator>
		<pubDate>Mon, 30 Jun 2008 23:10:17 +0000</pubDate>
		<guid isPermaLink="false">http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1642</guid>
		<description>[...] Although Google has begun to vertically integrate by building it&#8217;s own servers and reportedly it&#8217;s own switch, it&#8217;s hardly in control of all the resources required. In fact, none of the supposed five [...]</description>
		<content:encoded><![CDATA[<p>[...] Although Google has begun to vertically integrate by building it&#8217;s own servers and reportedly it&#8217;s own switch, it&#8217;s hardly in control of all the resources required. In fact, none of the supposed five [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Future of computing: Forecast calls for partly cloudy &#124; Bitcurrent</title>
		<link>http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1641</link>
		<dc:creator>Future of computing: Forecast calls for partly cloudy &#124; Bitcurrent</dc:creator>
		<pubDate>Thu, 12 Jun 2008 04:11:07 +0000</pubDate>
		<guid isPermaLink="false">http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1641</guid>
		<description>[...] infrastructure vendors as those complex products become increasingly strategic differentiators? Google has already been rumored to have developed their own 10GBit ethernet switch, presumably a crucial component in scaling their massively parallel [...]</description>
		<content:encoded><![CDATA[<p>[...] infrastructure vendors as those complex products become increasingly strategic differentiators? Google has already been rumored to have developed their own 10GBit ethernet switch, presumably a crucial component in scaling their massively parallel [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Andy</title>
		<link>http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1640</link>
		<dc:creator>Andy</dc:creator>
		<pubDate>Fri, 01 Feb 2008 06:22:15 +0000</pubDate>
		<guid isPermaLink="false">http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1640</guid>
		<description>Do you still think Arastra is a viable story after both Cisco and Juniper announced next generation Nexus and EX?
It is not hardware but the feature in software which decide the success. It is core business for both big networking companies and would be very hard for small companies like Arastra to break into that specially with one shot someone-elses-silica based approach.

As for Andy, many companies he funded have gone out of business so that is hardly a plus.</description>
		<content:encoded><![CDATA[<p>Do you still think Arastra is a viable story after both Cisco and Juniper announced next generation Nexus and EX?<br />
It is not hardware but the feature in software which decide the success. It is core business for both big networking companies and would be very hard for small companies like Arastra to break into that specially with one shot someone-elses-silica based approach.</p>
<p>As for Andy, many companies he funded have gone out of business so that is hardly a plus.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: 10GbE and SFP+ - This Time It&#8217;s Different &#124; Nyquist Capital</title>
		<link>http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1639</link>
		<dc:creator>10GbE and SFP+ - This Time It&#8217;s Different &#124; Nyquist Capital</dc:creator>
		<pubDate>Sat, 22 Dec 2007 01:08:55 +0000</pubDate>
		<guid isPermaLink="false">http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1639</guid>
		<description>[...] Investor Login           &#171; Google&#8217;s Secret 10GbE Switch [...]</description>
		<content:encoded><![CDATA[<p>[...] Investor Login           &laquo; Google&#8217;s Secret 10GbE Switch [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: KN</title>
		<link>http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1638</link>
		<dc:creator>KN</dc:creator>
		<pubDate>Wed, 19 Dec 2007 00:36:46 +0000</pubDate>
		<guid isPermaLink="false">http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1638</guid>
		<description>For those disputing the Google server count....I think you are making the assumption that these servers are 100% utilized. Many large server farms run at about 10-20% cpu utilization. So take any number you come up with and x7.
This is why virtualization is growing so rapidly. Even though the Hypervizer takes up 10% of the cpu, you end up getting another 10-20% use out of your server farm.</description>
		<content:encoded><![CDATA[<p>For those disputing the Google server count&#8230;.I think you are making the assumption that these servers are 100% utilized. Many large server farms run at about 10-20% cpu utilization. So take any number you come up with and x7.<br />
This is why virtualization is growing so rapidly. Even though the Hypervizer takes up 10% of the cpu, you end up getting another 10-20% use out of your server farm.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Network Jack &#187; Blog Archive &#187; A Gigabyte of Power</title>
		<link>http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1637</link>
		<dc:creator>Network Jack &#187; Blog Archive &#187; A Gigabyte of Power</dc:creator>
		<pubDate>Tue, 11 Dec 2007 00:02:23 +0000</pubDate>
		<guid isPermaLink="false">http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1637</guid>
		<description>[...] is the speculation that Google is building their own 10Gbit optical [...]</description>
		<content:encoded><![CDATA[<p>[...] is the speculation that Google is building their own 10Gbit optical [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Andrew Schmitt</title>
		<link>http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1635</link>
		<dc:creator>Andrew Schmitt</dc:creator>
		<pubDate>Thu, 06 Dec 2007 18:44:43 +0000</pubDate>
		<guid isPermaLink="false">http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1635</guid>
		<description>I do not want to close this thread to comments but please refrain from further back and forth about Myricom. I can assure you that only a small fraction of the readers here are interested in this.</description>
		<content:encoded><![CDATA[<p>I do not want to close this thread to comments but please refrain from further back and forth about Myricom. I can assure you that only a small fraction of the readers here are interested in this.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Patrick</title>
		<link>http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1634</link>
		<dc:creator>Patrick</dc:creator>
		<pubDate>Thu, 06 Dec 2007 18:38:03 +0000</pubDate>
		<guid isPermaLink="false">http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1634</guid>
		<description>Dear Ben,

Your technical knowledge of Myricom&#039;s implementation is wrong on several points:
* There is no IP-over-Myrinet protocol, it&#039;s actually Ethernet-over-Myrinet. The Ethernet frames are encapsulated into a Myrinet packet. These frames could carry IP, but also any other protocols that can run on Ethernet.
* The switching latency applies to all Myrinet packets, being Ethernet-over-Myrinet packets or MX-over-Myrinet packets. There is a larger latency overhead in the 10G Myrinet/Ethernet bridges on the edges, but you can have as many Myrinet hops (32-port crossbar) as you want between the bridges. So for a single crossbar switch, yes the latency in the Myricom solution would be higher than a single integrated Ethernet crossbar like Fulcrum&#039;s. However, the end-to-end latency is barely different for very large switches on the Myricom solution.

In this context, think about Myrinet as the internal switch network, like Cisco or other Ethernet switch vendors have their own proprietary internal switch networks.</description>
		<content:encoded><![CDATA[<p>Dear Ben,</p>
<p>Your technical knowledge of Myricom&#8217;s implementation is wrong on several points:<br />
* There is no IP-over-Myrinet protocol, it&#8217;s actually Ethernet-over-Myrinet. The Ethernet frames are encapsulated into a Myrinet packet. These frames could carry IP, but also any other protocols that can run on Ethernet.<br />
* The switching latency applies to all Myrinet packets, being Ethernet-over-Myrinet packets or MX-over-Myrinet packets. There is a larger latency overhead in the 10G Myrinet/Ethernet bridges on the edges, but you can have as many Myrinet hops (32-port crossbar) as you want between the bridges. So for a single crossbar switch, yes the latency in the Myricom solution would be higher than a single integrated Ethernet crossbar like Fulcrum&#8217;s. However, the end-to-end latency is barely different for very large switches on the Myricom solution.</p>
<p>In this context, think about Myrinet as the internal switch network, like Cisco or other Ethernet switch vendors have their own proprietary internal switch networks.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Ben</title>
		<link>http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1636</link>
		<dc:creator>Ben</dc:creator>
		<pubDate>Thu, 06 Dec 2007 15:38:30 +0000</pubDate>
		<guid isPermaLink="false">http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1636</guid>
		<description>Funny to see a mentioning of Cisco and Myricom on the same line, and even more to read the funny response of Greg.

If someone belives that Myricom will be able to beat Cisco on 10G switching he needs to visit his doctor. Even more, Myricom low latency is when using their proprietary protocol, someting like doing IP over myrinet. Doing true TCP/IP they are far behind. Check their web site. details...details....

and last, there are no much of 10G deployments now due to price price and price. When 10G will be mature, there will be only 2-3 companies. Cisco will be there.</description>
		<content:encoded><![CDATA[<p>Funny to see a mentioning of Cisco and Myricom on the same line, and even more to read the funny response of Greg.</p>
<p>If someone belives that Myricom will be able to beat Cisco on 10G switching he needs to visit his doctor. Even more, Myricom low latency is when using their proprietary protocol, someting like doing IP over myrinet. Doing true TCP/IP they are far behind. Check their web site. details&#8230;details&#8230;.</p>
<p>and last, there are no much of 10G deployments now due to price price and price. When 10G will be mature, there will be only 2-3 companies. Cisco will be there.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Tony Fisch</title>
		<link>http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1632</link>
		<dc:creator>Tony Fisch</dc:creator>
		<pubDate>Wed, 05 Dec 2007 19:45:09 +0000</pubDate>
		<guid isPermaLink="false">http://www.nyquistcapital.com/2007/11/16/googles-secret-10gbe-switch/#comment-1632</guid>
		<description>Mike, I am back from vacation and want to set your record straight.  Same for Greg.  I suggest that you do more research on solutions and deployments before you comment about Myricom, or any other company.  You look silly.

I have two friends that have been in two Google data centers in the past year and Juniper is a former client of mine and they have been there a few times too, right.

No shot at BRCM, but Google is far from deciding anything. They love to look, test, do mind melds and ponder the future.  They are very private on some fronts for a public company.

Google&#039;s recent announcements in wireless suggest that they want to do a lot of things.  Time will judge If they have tried to do things they should not be doing.

Last time I checked, Cisco gear that runs Ethernet is controlled by a legacy proprietary technology IOS, IOX, etc.  Proprietary = control over an item of property.  Cisco has built a massive company making IOS a standard non standard and have done quite the job controlling the enterprise and carrier network.  While CSCO is not in this dance others that are could have some control in their technology too.  Gee, it works well for the rest of the industry.

Mike, do not assume you know about technology, or who is even posting unless you want to be silly.

Andrew, good research.
Cheers to all.</description>
		<content:encoded><![CDATA[<p>Mike, I am back from vacation and want to set your record straight.  Same for Greg.  I suggest that you do more research on solutions and deployments before you comment about Myricom, or any other company.  You look silly.</p>
<p>I have two friends that have been in two Google data centers in the past year and Juniper is a former client of mine and they have been there a few times too, right.</p>
<p>No shot at BRCM, but Google is far from deciding anything. They love to look, test, do mind melds and ponder the future.  They are very private on some fronts for a public company.</p>
<p>Google&#8217;s recent announcements in wireless suggest that they want to do a lot of things.  Time will judge If they have tried to do things they should not be doing.</p>
<p>Last time I checked, Cisco gear that runs Ethernet is controlled by a legacy proprietary technology IOS, IOX, etc.  Proprietary = control over an item of property.  Cisco has built a massive company making IOS a standard non standard and have done quite the job controlling the enterprise and carrier network.  While CSCO is not in this dance others that are could have some control in their technology too.  Gee, it works well for the rest of the industry.</p>
<p>Mike, do not assume you know about technology, or who is even posting unless you want to be silly.</p>
<p>Andrew, good research.<br />
Cheers to all.</p>
]]></content:encoded>
	</item>
</channel>
</rss>
