[6461] in linux-scsi channel archive
Re: tagged queuing buggy drive?
daemon@ATHENA.MIT.EDU (jlewis@lewis.org)
Wed May 5 03:30:22 1999
Date: Tue, 4 May 1999 22:16:56 -0400 (EDT)
From: jlewis@lewis.org
To: Michele Comitini <mcm@glisco.it>
cc: Linux SCSI Mailing List <linux-scsi@vger.rutgers.edu>
In-Reply-To: <E10eoEG-0006lV-00@geltrude.mixad.it>
On Wed, 5 May 1999, Michele Comitini wrote:
> We have the same problems on a software RAID-0 stripe set of 3
> WIKING IIWLS using a 2940uw controller. The system does not freeze, but
> we have filesystem corruption very often. It looks like a TQ error here
> too.
On advice from Gerard Roudier, I've disabled write caching on the drives
using scsi-config and I've also reduced the queue depth on each drive.
The quantum XP32275W, defaults to write caching on...and also defaults to
an AWRE/ARRE recovery time of 0ms. I set that to 100ms for all the
drives. I also switched back to an Adaptech 2940uw (from BT-958) since
I'd borrowed the BT-958 while debugging the system.
I haven't had time to beat the crap out of the array with multiple bonnies
(and now that its full of squid objects, that's going to be hard to do),
but it's been running a big squid process for several hours with a queue
depth of 8 per device.
----don't waste your cpu, crack rc5...www.distributed.net team enzo---
Jon Lewis *jlewis@lewis.org*| Spammers will be winnuked or
System Administrator | nestea'd...whatever it takes
Atlantic Net | to get the job done.
_________http://www.lewis.org/~jlewis/pgp for PGP public key__________
-
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@vger.rutgers.edu
