> recall a bit back the problem whereby the ether address
> was showing up in NFS->NFS xfers, and how this was fixed
> the new le driver?  Well, I hate to be the bearer of bad
> news, but it appears that this problem still exists.

I'm willing to bet that something stupid in the networking code is
freeing memory then using it again later...  i think i've seen this
(or something similar) on the i386, and it usually blows the system
away...

unfortunately, it's not so easy to debug...  *sigh*



chris