From owner-freebsd-questions  Tue Jun 20  7:48:46 2000
Delivered-To: freebsd-questions@freebsd.org
Received: from rose.niw.com.au (app3022-2.gw.connect.com.au [203.63.119.4])
	by hub.freebsd.org (Postfix) with ESMTP
	id 55EA237BA12; Tue, 20 Jun 2000 07:48:30 -0700 (PDT)
	(envelope-from ian@niw.com.au)
Received: by rose.niw.com.au (Postfix, from userid 1000)
	id 7B7EB62D60; Wed, 21 Jun 2000 00:18:23 +0930 (CST)
Date: Wed, 21 Jun 2000 00:18:23 +0930
From: Ian West <ian@niw.com.au>
To: Nick Slager <nicks@albury.net.au>
Cc: scsi@freebsd.org, questions@freebsd.org
Subject: Re: Invalidating pack messages
Message-ID: <20000621001823.A32878@rose.niw.com.au>
References: <20000620172810.A84355@albury.net.au>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
X-Mailer: Mutt 1.0i
In-Reply-To: <20000620172810.A84355@albury.net.au>; from nicks@albury.net.au on Tue, Jun 20, 2000 at 05:28:10PM +1000
Sender: owner-freebsd-questions@FreeBSD.ORG
Precedence: bulk
X-Loop: FreeBSD.ORG

On Tue, Jun 20, 2000 at 05:28:10PM +1000, Nick Slager wrote:
> I have an issue here that is just about to make me start chewing carpet or
> gnawing furniture in frustration.
> 
> We build our own BSD servers - always have. Pretty much always with the same
> hardware.
> 
> The latest system I've built sporadically spews forth these messages on the
> console with reckless abandon:
> 
> 	(da0:ahc0:0:0:0): Invalidating pack
> 	(da0:ahc0:0:0:0): Invalidating pack
> 	(da0:ahc0:0:0:0): Invalidating pack
> 	(da0:ahc0:0:0:0): Invalidating pack
> 
> Occasionally, I get interspersed with this things like:
> 
> 	(da0:ahc0:0:0:0): SCB 0x29 - timed out while idle, SEQADDR == 0x9
> 	(da0:ahc0:0:0:0): Queuing a BDR SCB
> 	(da0:ahc0:0:0:0): no longer in timeout, status = 35b
> 
> The system is custom built as follows:
> 
> Asus P3B-F motherboard (both BIOS revisions 1004 and 1005)
> Adaptec 2940UW-Pro SCSI controller
> 1 Seagate 18Gb Baracuda drive
> 128Mb RAM
> Celeron 466MHz CPU (no overclocking!)
> 
> I have swapped out, individually, one at a time, each component of the SCSI
> subsystem - controller, cable, drive and terminator. I'm still getting the
> error message.
> 
> I pulled off the 4.0-RELEASE install that was on it and went back to
> 3.4-RELEASE; same problem.
> 
> After looking through the archives, I thought the 'Invalidating pack' message
> was a sure indicator of bad hardware/termination etc. Now I'm not so sure.
> 
> Anyone have some helpful suggestions?
> 
> Thanks,
> 
> 
> Nick.
> 
> -- 
>  From a Sun Microsystems bug report (#4102680):
>   "Workaround: don't pound on the mouse like a wild monkey."
> 
> 
> 
> To Unsubscribe: send mail to majordomo@FreeBSD.org
> with "unsubscribe freebsd-scsi" in the body of the message

I think it might be a driver issue with freebsd. I have a very new
system with 2 * 18G Seagate Cheetah drives connected to an Adaptec 29160
controller which was showing identical symptoms. I loaded OpenBSD to
check if it was hardware or software (grasping at straws) and it has
been running flat out for days since. (Looping make build, kind of like
make world). Justin Gibbs did mention that he had some ideas, and some
code which might be available after usenix, although I think this might
be more specific to the 29160 set. There is no sign of any problem at
all under OpenBSD, although the throughput seems to be less.
(~26Mbytes/sec as opposed to ~34MBytes/Sec)

Just an extra data point, it might not be hardware at all.

Cheers
Ian.


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