> becomes a problem.
> 
> Finally, things like RAIDframe *really* want the old MAXPHYS limit to go
> away so that they don't ultimately send 8k transfers to the disks.
yes! i think optimal raid configuration in where 1-disk part of stripe
is read by that disk in time comparable to it's access time.
> > Some drivers will also break (pciide should work but I've never checked - 
> > siop will definitively not work without changes).
> 
> pciide totally loses with transfers larger than 64k.  I'm surprised that siop
so no sense of trying with pciide?