[rbridge] Can someone explain Multi-Topology...its purpose, use, etc?

[Donald Eastlake]

Hi David,

On Wed, Mar 7, 2012 at 5:06 PM, David Klebanov <klebanov at cisco.com> wrote:
> Hi Donald,
>
> I wanted to comment on your reply here. In the context of TRiLL or any other
> Ethernet encapsulation technology, how do you deal with intermediate nodes
> that do not support DCB, but yet run TRiLL. Will you basically "loose" DCB
> function on that link inside the TRiLL environment?

Short answer: Yes -- but this has nothing to do with TRILL and
everything to do with having nodes that do not support DCB.

Long answer:

The goal of the DCB facilities we are talking about is to eliminate
loss due to queue overflow. To do that over a path for some particular
type of traffic (usually classified by priority) every queue along
that path (usually queues just exist at output ports) must support the
facility. So any device with more than two ports where you could have
multiple streams converging on one output port or even a device with
only two ports if they could be different speed, must support the
facility or you have lost the guarantees. And you also have to meet
various engineering criterion for bandwidth-delay-buffering.

I don't see that it has anything particular to do with "TRILL" or
"encapsulation". If any device along the path has a queue that could
overflow and it doesn't implement the flow control facilities you are
counting on, then you can't depend on not losing data in that queue.

If a path is appropriately engineered and the devices along it are
some mix of TRILL switches and 802.1 bridges and they all implement,
for example, PFC and ETS and have those enabled for priority-x frames,
you should never lose a priority-x frame along that path due to queue
overflow.

Thanks,
Donald
=============================
 Donald E. Eastlake 3rd   +1-508-333-2270 (cell)
 155 Beaver Street, Milford, MA 01757 USA
 d3e3e3 at gmail.com

> Thanks,
> David
>
>
> On 3/2/12 12:23 PM, "Donald Eastlake" <d3e3e3 at gmail.com> wrote:
>
>> Some people think congestion notification (CN) is important and some
>> think it isn't.
>>
>> If you are just talking about Priority Based Flow control (PFC, aka
>> "per priority pause") or just PFC and ETS, they are down in the
>> queueing control at ports and orthogonal to what sort of switch
>> protocol you are running above the ports. Could be a bridge, a layer 3
>> router, an RBridge, or whatever. PFC and ETS are pretty much the same.
>>
>> Thanks,
>> Donald
>> =============================
>>  Donald E. Eastlake 3rd   +1-508-333-2270 (cell)
>>  155 Beaver Street, Milford, MA 01757 USA
>>  d3e3e3 at gmail.com
>>
>> On Fri, Mar 2, 2012 at 2:48 PM,  <david.black at emc.com> wrote:
>>> That was a timely submission.
>>>
>>> My understanding is that while congestion notification was originally part of
>>> DCB, that's
>>> no longer considered to be the case.  Deployments of DCB Ethernet for FCoE
>>> typically do
>>> not include congestion notification.
>>>
>>> Thanks,
>>> --David
>>>
>>>> -----Original Message-----
>>>> From: Donald Eastlake [mailto:d3e3e3 at gmail.com]
>>>> Sent: Friday, March 02, 2012 2:39 PM
>>>> To: Black, David
>>>> Cc: narten at us.ibm.com; rbridge at postel.org
>>>> Subject: Re: [rbridge] Can someone explain Multi-Topology...its purpose,
>>>> use, etc?
>>>>
>>>> On Fri, Mar 2, 2012 at 1:21 PM,  <david.black at emc.com> wrote:
>>>>> Note that using FCoE over TRILL essentially requires that TRILL support DCB
>>>>> Ethernet.
>>>>
>>>> See https://datatracker.ietf.org/doc/draft-eastlake-trill-rbridge-dcb/
>>>>
>>>> Thanks,
>>>> Donald
>>>> =============================
>>>>  Donald E. Eastlake 3rd   +1-508-333-2270 (cell)
>>>>  155 Beaver Street, Milford, MA 01757 USA
>>>>  d3e3e3 at gmail.com
>>>>
>>>>> Thanks,
>>>>> --David
>>>>>
>>>>>> -----Original Message-----
>>>>>> From: rbridge-bounces at postel.org [mailto:rbridge-bounces at postel.org] On
>>>>>> Behalf Of Thomas Narten
>>>>>> Sent: Friday, March 02, 2012 8:26 AM
>>>>>> To: Radia Perlman
>>>>>> Cc: rbridge at postel.org
>>>>>> Subject: Re: [rbridge] Can someone explain Multi-Topology...its purpose,
>>>>>> use, etc?
>>>>>>
>>>>>>> 3) Specifically for TRILL, why would multi-topology be useful?
>>>>>>
>>>>>> Disjoint multipathing for FCoE. Today, many FC deployments use
>>>>>> physically replicated SANs. Twice the cabling/cost/etc.
>>>>>>
>>>>>> But, there is real value in terms of fault isolation in having
>>>>>> completely disjoint paths.
>>>>>>
>>>>>> TRILL, today, does not really do this.
>>>>>>
>>>>>> Thomas
>>>>>>
>>>>>> _______________________________________________
>>>>>> rbridge mailing list
>>>>>> rbridge at postel.org
>>>>>> http://mailman.postel.org/mailman/listinfo/rbridge
>>>>>
>>>>>
>>>>> _______________________________________________
>>>>> rbridge mailing list
>>>>> rbridge at postel.org
>>>>> http://mailman.postel.org/mailman/listinfo/rbridge
>>>
>>
>> _______________________________________________
>> rbridge mailing list
>> rbridge at postel.org
>> http://mailman.postel.org/mailman/listinfo/rbridge
>