[ofa-general] Re: [RFC] OpenSM and IPv6 Scalability Proposal

Hal Rosenstock hrosenstock at xsigo.com
Mon Jun 16 09:06:35 PDT 2008


On Mon, 2008-06-16 at 18:51 +0300, Sasha Khapyorsky wrote:
> On 08:26 Mon 16 Jun     , Hal Rosenstock wrote:
> > On Mon, 2008-06-16 at 18:07 +0300, Sasha Khapyorsky wrote:
> > > On 07:48 Mon 16 Jun     , Hal Rosenstock wrote:
> > > > > 
> > > > > I would think so, but didn't check deeply. And in fact actual size of
> > > > > such array can be limited by max supported number of MLIDs in a fabric
> > > > 
> > > > Is that really a good idea to limit it in this way ? Guess it could be
> > > > limited with some configurable option but even so if a device with a
> > > > larger MFT comes along then the SM might not work.
> > > 
> > > I meant something else - any multicast stuff will be processed in SM
> > > after initial subnet discovery, so it is not a big problem to detect
> > > max needed array size in run-time.
> > 
> > Isn't a similar thing done in terms of unicast ?
> 
> Yes, with cl_vector*() and it is *slow*.

If 16K array of pointers is OK, is a 48K array ? If so, then this should
be straightforward to change.

-- Hal

> Sasha
> _______________________________________________
> 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




More information about the general mailing list