[ofa-general] Cisco 7008 Internal/External Port Mappings

[Ted Wilcox (tewilcox)]

Attached is a text file (unix file format) with the port mappings.  As
you surmised, the leaf chips are in slots 9, 10, 13, 14, and the spines
are in 11, 12.  Our nomenclature is that the leaf cards are "Node" cards
(Node 1 = Slot 9, Node 2 = Slot 10, etc.) and the spine cards are "Core"
cards (Core 1 = slot 11, Core 2 = slot 12).  I apologize for the
somewhat goofy naming; it came from the early hardware design.

If you're running the Cisco SM, we have recently released a pretty
general-purpose network debugging/maintenance tool called FACT which may
help you out
(http://tools.cisco.com/support/downloads/go/Redirect.x?mdfid=279966112
-- look under "Server Fabric Software").  It requires a cisco.com login,
but not a support contract.

-Ted.

P.S. I don't generally keep up with ofa-general (my apologies), so
please cc' me on any replies, flames, etc.

-----Original Message-----
From: general-bounces at lists.openfabrics.org
[mailto:general-bounces at lists.openfabrics.org] On Behalf Of Charles
Taylor
Sent: Thursday, July 10, 2008 4:15 PM
To: general-list
Subject: Re: [ofa-general] Cisco 7008 Internal/External Port Mappings


Nope.   Looks pretty much the same as ibnetdiscover without the "- 
g".    It would be really useful if it *did* work.  :)

Thanks for the suggestion though.     I think we just may be stuck  
mapping it empirically.    I'm sure the pattern will become obvious  
quickly enough.

Charlie Taylor
UF HPC Center

On Jul 10, 2008, at 5:36 PM, Hal Rosenstock wrote:

> On Thu, 2008-07-10 at 17:27 -0400, Charles Taylor wrote:
>> We've got a couple of Cisco 7008/Topspin 270 core switches.    Much  
>> of
>> the diagnostic and topology information we get from the ib diag tools

>> in OFED refer to the internal ports rather than the actual external 
>> slot/port.
>
> Does ibnetdiscover -g work ? There was some work done to do this 
> mapping for Cisco but it may be out of date.
>
> -- Hal
>
>>    We could deduce the mappings, I suppose, by tracing cables and 
>> using ibtracert between nodes but that seems like a real
>> pain.    I was wondering if anyone on this list knows how that  
>> mapping
>> works.     The chassis itself consists of 8 "ib port" blades in the
>> front labelled as slots 1 - 8.   There are then six "fabric
>> controller" slots in the back of the chassis labelled 9 - 14.
>> Slots 11 and 12 are "special" as they hold the "master" and "standby 
>> master" fabric controllers.
>>
>> Seems like the FC's in slots 11 and 12 connect the the FCs in slots
>> 9,10,13,14 which in turn connect to the external port blades in slots
>> 1 - 8.
>>
>> Again, all of the diagnostic information refers to the internal FC 
>> ports and mapping those to the external ports (to which we actually
>> connect leaf switches) seems non-trivial.    I think there was even a
>> document somewhere that described the mapping.   We just can't find  
>> it
>> now.
>>
>> Thanks,
>>
>> Charlie Taylor
>> UF HPC Center
>> _______________________________________________
>> general mailing list
>> general at lists.openfabrics.org
>> http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
>>
>> To unsubscribe, please visit 
>> http://openib.org/mailman/listinfo/openib-general
>

_______________________________________________
general mailing list
general at lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general

To unsubscribe, please visit
http://openib.org/mailman/listinfo/openib-general
-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: TS270_port_mapping.txt
URL: <http://lists.openfabrics.org/pipermail/general/attachments/20080711/206dcfc5/attachment.txt>