Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 17 Apr 2000 11:25:53 -0400 (EDT)
From:      David Miller <dmiller@search.sparks.net>
To:        Parag Patel <parag@cgt.com>
Cc:        Morgan Davis <mdavis@cts.com>, freebsd-stable@FreeBSD.ORG
Subject:   Re: 4.0-stable + SMP + fxp = device timeout 
Message-ID:  <Pine.BSF.4.21.0004171120420.37139-100000@search.sparks.net>
In-Reply-To: <26709.954359726@pinhead.parag.codegen.com>

next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, 29 Mar 2000, Parag Patel wrote:

> On Wed, 29 Mar 2000 01:01:27 PST, "Morgan Davis" wrote:
> >
> >The subject says it all.  Is this a known problem with SMP and the fxp
> >driver? (Checked 4.0 errata and searched the mailing lists -- didn't see
> >anything).
> 
> Works just fine here on my dual PII/300 ASUS P97-DS motherboard.  dmesg
> output appended below.  The machine has been up since Sunday and
> survived a "make -j8 buildworld", plays audio fine (tho' recording seems
> to have problems), and in short seems pretty happy.


Sorry to be so late, but I thought I had an interesting data point....


A month or so back I was working on a ncr driver issue crashing a
3.4-stable system.  I had a simple torutre test which a) ran a dozen or so
cpu-bound programs, b) ran a dozen random IO disk benchmarks, and c) got
ping flooded by a couple of other hosts.

The results were:

with ncr0 driver, system would crash in an hour or two
with sym0 driver, system chugged away for days.
with ahc driver on a 2940U2w the fxp would timeout every 30 seconds or so.

This was a 3.4 stable system on a 2x500 P-III Intell NLX440 MB in a 2U
case.  SMP was enabled, no IRQ's were shared.  I never had a chance to
investigate it further:(

--- David Miller



To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-stable" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.4.21.0004171120420.37139-100000>