Regards, Dave
----- Original Message -----
From: Peter Desnoyers <pjd@fred001.dynip.com>
To: Paradox <paradox3@maine.rr.com>
Sent: Sunday, September 19, 1999 11:07 PM
Subject: Re: eth0 slow down..
> Paradox wrote:
> >
> > I have a cable modem running 2.2.11 with "pump" as my dhcp client,
RH6.0...I
> > notice that every now and then the connection will seem to become super
> > slow...ping's to another computer on the network (the gateway) go up to
> > 20000 ms...however, a tcpdump shows that the pings are returned
immediately
> > and other computers on the network are fine (full speed)..apparently
there
> > is something going on internally causing this slow down. What I do is
bring
> > eth0 down and then run pump again, and then it works fine (i get 6 ms
> > pings)...for a while.
> >
> > I'm running 2.2.11 SMP, the ethernet card is an NE2000 compatible PCI I
> > believe.
> > BTW, this doesn't ever seem to affect eth1, my lan.
>
> I've run into this, too. Oddly enough, on another Roadrunner system
> (MediaOne). I used to get the problem on a tulip board, but now I've got
> an NE2000 clone. I haven't seen the issue in weeks now, but used to
> get it in spades not long after upgrading to redhat 6.0; also, several
> other people on the local newsgroup had the problem.
>
> Just a thought - do you have a cyrix CPU? I think my trouble went away
> when I switched to an AMD, and I know (from painful experience with a
> driver I'm developing) that there are some issues with Cyrixen and PCI.
> (DMA consistency in particular, but maybe others)
>
> --
>
............................................................................
> Peter Desnoyers
> 162 Pleasant St. (617) 661-1979 pjd@fred.cambridge.ma.us
> Cambridge, Mass. 02139 (978) 461-0402 (work) pjd@giga-net.com
>
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/