[PATCH] if_sk(4) rx/tx "hangs"

Maxime Henrion mux at freebsd.org
Sat Nov 13 14:22:30 GMT 2004

Bjoern A. Zeeb wrote:
> On Fri, 12 Nov 2004, Peter Wemm wrote:
> > > Try something less CPU intensive like /dev/zero :)
> >
> > I think he was saying he created a 1GB file from the contents
> > of /dev/urandom and then timed the transfer of this over 100Mbit/sec
> > link.
> that's it but I had been to lazy to tell you the whole dd story in te
> middle of the night.
> I preffer random data when sometimes testing over ssh all zero get's
> easily compressed ;)
> > Anyway, the point was that it worked!  Could the problem with the K8V SE
> > really be as simple as we've been hardcoding 128K of ram for a device
> > that only has 64K?
> It's not directly a matter of the K8V SE.
> It's the 88E8001 (but at least my K8V SE deluxe has this one acording
> to the PN from VPD data).
> The 88E8010 already has 128k according to the pdf mentioned in my diff.
> Anyone actually tested it ? Mine still seems to be fine after the
> night.

I have this exact model (skc0: PN: Yukon 88E8001) in my work computer.
I had to use another NIC since this once was constantly wedging when
sending too much data.  I'll give this patch a try on Monday and let you


More information about the freebsd-amd64 mailing list