sgai at nuovasystems.com
Thu Oct 19 08:07:51 PDT 2006
IMO we should avoid variable length matching in transit bridges. Fixed
length is easy to handle with a hash function.
> -----Original Message-----
> From: rbridge-bounces at postel.org [mailto:rbridge-bounces at postel.org]
> Behalf Of Erik Nordmark
> Sent: Wednesday, October 18, 2006 11:06 AM
> To: Radia Perlman
> Cc: rbridge at postel.org
> Subject: [rbridge] LIDs
> Radia Perlman wrote:
> > We haven't discussed the LID fields. Perhaps that should be a
> > thread. Since that doesn't
> > affect forwarding, and is only a convenience to the egress RBridge,
> > doesn't seem too compelling.
> > The ingress RBridge has to do the lookup per endnode, so it's only
> > most twice as much computation
> > for a Designated RBridge to have to do the lookup both when a packet
> > leaves its link and when it enters.
> If we are trying to squeeze bits and see a need for a LID capability,
> might make sense to allow different egress rbridges have different
> number of LID bits - they only need to number their ports so in some
> cases few bits would be sufficient.
> Assuming we have a 19 bit space for RBridge alias plus LID, then an
> rbridge with 16 ports would ask for an alias that is 19-4=15 bits.
> The downside of such an approach is that the alias setup would need to
> be able to handle variable length aliases, and the transit rbridges
> would either need variable length matching on the RBridge alias, or
> expand out to all the matching 19 bit patterns and have the hardware
> full 19 bit matches. For instance, the above 15 bit alias would expand
> to 16 different matches on 19 bits.
> rbridge mailing list
> rbridge at postel.org
More information about the rbridge