Message-ID: <3FD74AE2.2010600@acu.ac.uk>
Date: Wed, 10 Dec 2003 16:33:38 +0000
From: Mike Brodbelt <m.brodbelt@acu.ac.uk>
User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.0.0) Gecko/20020623 Debian/1.0.0-0.woody.1
MIME-Version: 1.0
To: "Jeffrey E. Hundstad" <jeffrey.hundstad@mnsu.edu>
CC: linux-xfs@oss.sgi.com
Subject: Re: XFS filesystem shutdown
References: <3FD5ED83.7000500@acu.ac.uk> <1432.10.1.200.117.1071040970.squirrel@imap01.ch.sauter-bc.com> <3FD6F55A.2060707@acu.ac.uk> <3FD6F719.7090009@epost.de> <3FD6F906.9070603@acu.ac.uk> <3FD74730.9070602@mnsu.edu>
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Sender: linux-xfs-bounce@oss.sgi.com
Errors-to: linux-xfs-bounce@oss.sgi.com
Precedence: bulk
Content-Length: 1672
Lines: 32

Jeffrey E. Hundstad wrote:
> What enclosures are you using for your drives?  We had a ICP vortex card 
> with CI-design enclosures we bought that we're supposed to be 
> ultra-160.

I have had enclosure problems on that machine in the past. I have U160
drives, but I've got the sync rate set down to 80, as I was getting an
unacceptably high level of retries, and I had disks reported as failed
when they were fine. Operating at 80MB, they seem to be OK, though I
have seen some retries. I have been operating on the assumption (as
there's nothing in the controller's event log) that the host OS would
see only good data from the controller even where a disk retry occurs.

> As it tuns out when we opened the CI-design enclosures they 
> didn't meet any of the ultra-160 design goals.  ...We threw out the 
> enclosures and the ICP vortex card works fine.  ...We only had problems 
> with the enclosure setup when a drive had a little problems -- soft 
> retries for example, then it threw the whole scsi channel into 
> disarray.  Many disks LOOKED as if it had a problem, it of course nuked 
> the raid-5 array.  ...If you checked each drive individually each drive 
> succeeded (including the original failed disk.)  ...and I could run 
> bonnie++ on it for weeks.  ...but several days into a production run it 
> would fail.

I have a second machine, also running an ICP controller and XFS, but
with ICY DOCK caddies. These operate perfectly with SCA disks at U160.
This machine has never reported any XFS errors, so I suppose it may be
worth my while purchasing new caddies and swapping them out. Unreliable
SCSI chains are certainly not much fun at all....

Mike.