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

[Sean Hefty]

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

- Sean