Comments on: Correction: There Might be an End-to-End FCoE Solution http://blog.scottlowe.org/2009/07/30/correction-there-might-be-an-end-to-end-fcoe-solution/ The weblog of an IT pro specializing in virtualization, storage, and servers Wed, 08 Feb 2012 17:13:47 +0000 hourly 1 http://wordpress.org/?v= By: Bud http://blog.scottlowe.org/2009/07/30/correction-there-might-be-an-end-to-end-fcoe-solution/comment-page-1/#comment-49153 Bud Mon, 13 Sep 2010 19:23:25 +0000 http://blog.scottlowe.org/?p=1501#comment-49153 Wow this post is over a year old and still no End-to-End connectivity from the UCS B-Series to storage. Cisco's marketing hype on converged networks is confusing. Wow this post is over a year old and still no End-to-End connectivity from the UCS B-Series to storage. Cisco’s marketing hype on converged networks is confusing.

]]> By: slowe http://blog.scottlowe.org/2009/07/30/correction-there-might-be-an-end-to-end-fcoe-solution/comment-page-1/#comment-47353 slowe Thu, 21 Jan 2010 13:17:14 +0000 http://blog.scottlowe.org/?p=1501#comment-47353 JD, The standardization of DCB/CEE will lead to multi-vendor FCoE interoperability. Even though FC-BB-5 has been finalized (not yet a formal standard, but finalized) and the "FC" side of FCoE has been locked down for multiple vendors to implement, the "oE" side of FCoE depends upon DCB/CEE. When that is finalized, I expect that more vendors will jump on board and uptake of the technology will increase significantly. JD,

The standardization of DCB/CEE will lead to multi-vendor FCoE interoperability. Even though FC-BB-5 has been finalized (not yet a formal standard, but finalized) and the “FC” side of FCoE has been locked down for multiple vendors to implement, the “oE” side of FCoE depends upon DCB/CEE. When that is finalized, I expect that more vendors will jump on board and uptake of the technology will increase significantly.

]]> By: jd http://blog.scottlowe.org/2009/07/30/correction-there-might-be-an-end-to-end-fcoe-solution/comment-page-1/#comment-47350 jd Thu, 21 Jan 2010 00:33:13 +0000 http://blog.scottlowe.org/?p=1501#comment-47350 Scott, Great blog. Thanks for all the info. What's your take on the current state of the standards at play here, FC-BB-5 and IEEE's DCB (or CEE). DCB hasn't been finalized. Should that concern anyone considering adopting this technology? Is the fact that FC-BB-5 is in draft format and is not ANSI standard at this point just a formality? Thanks. Scott,

Great blog. Thanks for all the info.

What’s your take on the current state of the standards at play here, FC-BB-5 and IEEE’s DCB (or CEE). DCB hasn’t been finalized. Should that concern anyone considering adopting this technology? Is the fact that FC-BB-5 is in draft format and is not ANSI standard at this point just a formality? Thanks.

]]> By: slowe http://blog.scottlowe.org/2009/07/30/correction-there-might-be-an-end-to-end-fcoe-solution/comment-page-1/#comment-46066 slowe Tue, 29 Sep 2009 12:19:03 +0000 http://blog.scottlowe.org/?p=1501#comment-46066 Craig, You can run the Nexus 5000, CNAs in your servers, and FCoE interfaces on the storage and use end-to-end FCoE *AS LONG AS* you don't exceed the switch port capacity of a Nexus 5000. If you need more ports than a single N5K can provide, you can't add another N5K and continue to get end-to-end FCoE. Cisco is adding/has added FIP (FCoE Initialization Protocol) support to NX-OS in a new release for the N5K, but as far as I am aware the issue of transporting VLAN/VSAN IDs across VE_Ports between two N5Ks has not yet been addressed. Craig,

You can run the Nexus 5000, CNAs in your servers, and FCoE interfaces on the storage and use end-to-end FCoE *AS LONG AS* you don’t exceed the switch port capacity of a Nexus 5000. If you need more ports than a single N5K can provide, you can’t add another N5K and continue to get end-to-end FCoE. Cisco is adding/has added FIP (FCoE Initialization Protocol) support to NX-OS in a new release for the N5K, but as far as I am aware the issue of transporting VLAN/VSAN IDs across VE_Ports between two N5Ks has not yet been addressed.

]]> By: Craig http://blog.scottlowe.org/2009/07/30/correction-there-might-be-an-end-to-end-fcoe-solution/comment-page-1/#comment-46062 Craig Tue, 29 Sep 2009 07:51:48 +0000 http://blog.scottlowe.org/?p=1501#comment-46062 As for today, UCS do not provide end to end FCoE due to the limitation apply on the UCS 6100. If you run the nexus 5000, CNA adapter and FCoE interface on your storage, you will have the end to end solution. As for today, UCS do not provide end to end FCoE due to the limitation apply on the UCS 6100. If you run the nexus 5000, CNA adapter and FCoE interface on your storage, you will have the end to end solution.

]]> By: Serge Meeuwsen http://blog.scottlowe.org/2009/07/30/correction-there-might-be-an-end-to-end-fcoe-solution/comment-page-1/#comment-45325 Serge Meeuwsen Sun, 02 Aug 2009 12:58:20 +0000 http://blog.scottlowe.org/?p=1501#comment-45325 Scott, Thanks again for keeping us all informed, very useful and educational indeed. With regards to UCS end-to-end (scalable) support for FCoE, I would assume that all that would required at a future date is updating firmware and such of all interconnecting devices? Though that might be a big assumption... :-) Cheers, Serge M Scott,
Thanks again for keeping us all informed, very useful and educational indeed.

With regards to UCS end-to-end (scalable) support for FCoE, I would assume that all that would required at a future date is updating firmware and such of all interconnecting devices? Though that might be a big assumption… :-)

Cheers,
Serge M

]]> By: slowe http://blog.scottlowe.org/2009/07/30/correction-there-might-be-an-end-to-end-fcoe-solution/comment-page-1/#comment-45307 slowe Fri, 31 Jul 2009 17:30:48 +0000 http://blog.scottlowe.org/?p=1501#comment-45307 Yes, fabric extenders change the story quite dramatically. I'll need a separate post for that! Yes, fabric extenders change the story quite dramatically. I’ll need a separate post for that!

]]> By: Brad Hedlund http://blog.scottlowe.org/2009/07/30/correction-there-might-be-an-end-to-end-fcoe-solution/comment-page-1/#comment-45306 Brad Hedlund Fri, 31 Jul 2009 17:02:59 +0000 http://blog.scottlowe.org/?p=1501#comment-45306 Scott, Excellent summary! You may not claim to be an FCoE expert but you are becoming one quickly. As for your statement: "...pre-FIP initiators or targets on the same IEEE DCB-capable Layer 2 switch (not an FCF); I suspect they would not be able to communicate." You are correct! Unless, if the pre-FIP initiators and targets are connected to a "Fabric Extender", then things start to get interesting :-) Cheers, Brad Scott,
Excellent summary! You may not claim to be an FCoE expert but you are becoming one quickly.

As for your statement: “…pre-FIP initiators or targets on the same IEEE DCB-capable Layer 2 switch (not an FCF); I suspect they would not be able to communicate.”

You are correct!

Unless, if the pre-FIP initiators and targets are connected to a “Fabric Extender”, then things start to get interesting :-)

Cheers,
Brad

]]> By: Dejan Ilic http://blog.scottlowe.org/2009/07/30/correction-there-might-be-an-end-to-end-fcoe-solution/comment-page-1/#comment-45303 Dejan Ilic Fri, 31 Jul 2009 08:36:33 +0000 http://blog.scottlowe.org/?p=1501#comment-45303 Hello, I was wondering what FIP was used for, as you text implies the possibility of existence of devices without it that can communicate, and found that there is a Wikipedia-page explaining some definition. http://en.wikipedia.org/wiki/Fibre_Channel_over_Ethernet You might want to include a link to it in your pages regarding FCoE. Regarding FIP, I'm still not sure what the purpose is (beside the obvious) and which protocol it replaces. Hello,
I was wondering what FIP was used for, as you text implies the possibility of existence of devices without it that can communicate, and found that there is a Wikipedia-page explaining some definition.

http://en.wikipedia.org/wiki/Fibre_Channel_over_Ethernet

You might want to include a link to it in your pages regarding FCoE.
Regarding FIP, I’m still not sure what the purpose is (beside the obvious) and which protocol it replaces.

]]> By: slowe http://blog.scottlowe.org/2009/07/30/correction-there-might-be-an-end-to-end-fcoe-solution/comment-page-1/#comment-45301 slowe Fri, 31 Jul 2009 04:31:40 +0000 http://blog.scottlowe.org/?p=1501#comment-45301 The UCS 6100 fabric interconnects are based on Nexus 5000 technologies, but the two products are not the same. Trust me, I've had the same discussions with the Cisco UCS folks. For now, you can't make comparisons between the UCS 6100 fabric interconnects and the Nexus 5000 family of switches. The UCS 6100 fabric interconnects are based on Nexus 5000 technologies, but the two products are not the same. Trust me, I’ve had the same discussions with the Cisco UCS folks. For now, you can’t make comparisons between the UCS 6100 fabric interconnects and the Nexus 5000 family of switches.

]]>