Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 17 Dec 2009 13:34:55 -0800
From:      Chuck Swiger <cswiger@mac.com>
To:        Erik Norgaard <norgaard@locolomo.org>
Cc:        questions@freebsd.org
Subject:   Re: System crashes under heavy disk i/o
Message-ID:  <69AC657B-A0A7-41CA-92F6-989FEFEB776E@mac.com>
In-Reply-To: <4B2AA1F4.5020206@locolomo.org>
References:  <4B2AA1F4.5020206@locolomo.org>

next in thread | previous in thread | raw e-mail | index | archive | help
Hi--

On Dec 17, 2009, at 1:26 PM, Erik Norgaard wrote:
> FreeBSD 8.0-RELEASE-p1 #0: Fri Dec 11 11:53:19 CET 2009
>    norgaard@localhost:/usr/local/obj/usr/local/src/sys/GENERIC
> Timecounter "i8254" frequency 1193182 Hz quality 0
> CPU: VIA Nehemiah (800.04-MHz 686-class CPU)
>  Origin = "CentaurHauls"  Id = 0x69a  Stepping = 10
> real memory  = 268435456 (256 MB)
> avail memory = 231383040 (220 MB)
> atapci0: <VIA 6420 SATA150 controller>
> ad6: 476940MB <Seagate ST3500320NS SN04> at ata3-master SATA150
> 
> In normal operation I have no problem, but when performing intensive read or write for a prolonged time the system crashes. This happens also even if the partition is read-only. The crash occurs both with single large files (1GB) as well as many small files (10kb-10MB).

That's probably a sign of either thermal problems from inadequate cooling, or possibly PSU not giving stable voltage rails and sagging a bit too low; also, at least the older VIA C3 EPIA hardware had somewhat flaky PATA interfaces; if I tried to use both PATA channels I'd see lockups, unless I turned everything down to UDMA-33 speeds.  

Hopefully their SATA implementation has been improved since.  Consider looking at smartctl and see whether your drive temps are running too hot-- supposedly, drives are rated up to around 60C, but I don't like to see drives going above 40C given any choice in the matter.

Regards,
-- 
-Chuck




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?69AC657B-A0A7-41CA-92F6-989FEFEB776E>