Subject: Re: Serious SCB Timeout problems in 2.0.2 on Alpha w/ fxp devices
To: Stephen Jones <smj@cirr.com>
From: Dave Huang <khym@azeotrope.org>
List: tech-kern
Date: 06/26/2005 13:21:40
On Sun, Jun 26, 2005 at 10:34:09AM -0700, Stephen Jones wrote:
> On Jun 26, 2005, at 9:22 AM, Christos Zoulas wrote:
> >Maybe it is the amount of traffic that is different? I.e. How much
> >traffic do you push through the interface daily?
> 
> I'm not sure that really matters.  On the two production CS20s the 
> errors always occur on the fxp1
> interface and almost never on the fxp0 interface.  This could be why 
> people always reply with
> "I don't see this problem" since they probably only have one interface 
> active anyway.

Ah, yeah, I only have one NIC in that machine. I found your PR
(port-alpha/30560), and it made it sound like you get errors simply by
having an fxp in the system ("How-To-Repeat: Install any 2.x release
of NetBSD on an Alpha with fxp (i82557) ethernet interface(s)
configured.")

FWIW,

yerfable ~> netstat -bIfxp0 | head -2
Name  Mtu   Network       Address               Ibytes     Obytes
fxp0  1500  <Link>        00:a0:c9:13:61:7e 7872415366 16721268625
yerfable ~> uptime
 1:14PM  up 32 days, 21:12, 7 users, load averages: 0.52, 0.51, 0.33

Which works out to an average of 5885 bytes/sec out and 2771 bytes/sec
in. I tried running ttcp between the alpha and another machine, and
didn't get any errors in that case either.