[ewg] Re: [ofa-general] RE: OFED 1.2 beta blocking bugs

[Hal Rosenstock]

On Thu, 2007-03-08 at 17:56, Sean Hefty wrote:
> > I'm talking about IP multicast not IB multicast, so the hardware MTU
> > should be transparent.
> 
> The IP multicast message would need fragmentation though if the hardware MTU 
> were too small.

IP does this fragmentation and would need to do this to UD MTU size not
the RC (CM) size.

>   If fragmentation wasn't occurring, then getting a local length 
> error might be expected.

Or what about the other way around, if it tried to make the MTU too
large ?

>   I'm not familiar with the IPoIB CM code (looking at it 
> now), but I wouldn't expect the CM related code to affect multicast traffic.

I would as IPoIB-CM does not support MC and there needs to be a fallback
to UD. I'm not sure where IPmc gets the device MTU from but it may be
the wrong one (from CM rather than the normal UD interface). Has anyone
tracked this down ? I haven't had a chance to look yet.

-- Hal

> - Sean
> _______________________________________________
> 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