Re: [mpls] draft-fang-mpls-label-forwarding-no-swap - how much does it really save?

[Jeff Tantsura <[e-mail]>]

Experience talks ;-)

Would be really great to get quantification.

Regards,
Jeff

On Jul 24, 2015, at 5:09 PM, Eric C Rosen <[e-mail]> wrote:

>> When standard defines a "no-swap" operation,  ASIC engineer would
>> implement such operation completely differently
> 
> Well, this is where we came in.  The RFCs do not dictate how the ASICs
> should be designed, and your ASIC designers are free to design in
> whatever way best meets the needs of the systems that are going to use
> those ASICs.  You can put in any optimizations you think are warranted.  If you expect the ASICs to be used in products that will never need to swap label values, never need to push labels, never need to pop labels, then you are free to design the ASICs without any of these features.  If you think that these operations are needed, but that "don't change the label value or the stack size" are the most common operations, you can certainly optimize your design for that case.
> 
> But if you think you can get the ASICs designed properly simply by handing the RFCs to the ASIC designers, you may be in for an unpleasant surprise.
> 
>> Since the label is to be "swap"ed with a new LABEL stack, then the
>> design of SWAPPING need to consider TTL handling such as 1) just
>> decrement of original TTL or 2) using a brand new TTL, such as using
>> local new register stored value to Fill the sawp'ed new label stack.
> 
> The TTL handling is exactly the same for both cases.  If you have been telling your ASIC designers something different, you most definitely are in for an unpleasant surprise.
> 
> 
> 
> 
> 
> 
> _______________________________________________
> mpls mailing list
> [e-mail]
> https://www.ietf.org/mailman/listinfo/mpls