From: Michael Clark <michael@metaparadigm.com>
To: Andrew Morton <akpm@digeo.com>
Cc: linux-kernel@vger.kernel.org, Andrea Arcangeli <andrea@suse.de>
Subject: Re: 2.4.19pre10aa4 OOPS in ext3 (get_hash_table, unmap_underlying_metadata)
Date: Thu, 26 Sep 2002 15:56:56 +0800 [thread overview]
Message-ID: <3D92BDC8.8080603@metaparadigm.com> (raw)
In-Reply-To: 3D92B6F3.1428A76A@digeo.com
On 09/26/02 15:27, Andrew Morton wrote:
> Michael Clark wrote:
>
>>Hiya,
>>
>>Been having frequent (every 4-8 days) oopses with 2.4.19pre10aa4 on
>>a moderately loaded server (100 users - 0.4 load avg).
>>
>>The server is a Intel STL2 with dual P3, 1GB RAM, Intel Pro1000T
>>and Qlogic 2300 Fibre channel HBA.
>>
>>We are running qla2300, e1000 and lvm modules unmodified as present in
>>2.4.19pre10aa4. We also have quotas enabled on 1 of the ext3 fs.
>>
>
>
> It's not familiar, sorry.
Maybe I should try XFS? I've heard of people running this for
80+ days and no downtime. I really would like to get past 8 days.
> People are saying unkind things about the qlogic driver, and
Yes i know. My experience seems to be bad fault recovery after
a LIP reset although the driver in 2.4.19pre10aa4 seems okay
(have tested loop interruption under IO heavy load).
> the new version in Andrea's latest patchset is definitely
> faster than before. Might be worth a shot.
So, is possible for qlogic driver to be doing naughty things
with bufferheads? or is it more likely in the fs?
Anyone out there running a reasonably busy fileserver with
qlogic FC HBA and using ext3 or XFS with quotas? What
kernel/qlogic driver combo?
~mc
next prev parent reply other threads:[~2002-09-26 7:51 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-09-26 5:57 2.4.19pre10aa4 OOPS in ext3 (get_hash_table, unmap_underlying_metadata) Michael Clark
2002-09-26 7:27 ` Andrew Morton
2002-09-26 7:56 ` Michael Clark [this message]
2002-09-26 8:02 ` Andrew Morton
2002-09-26 11:12 ` Andrea Arcangeli
2002-09-26 11:43 ` Michael Clark
2002-09-26 9:21 ` Mario Mikocevic
2002-09-26 9:53 ` Michael Clark
2002-09-26 11:13 ` Mario Mikocevic
2002-09-26 11:48 ` Michael Clark
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=3D92BDC8.8080603@metaparadigm.com \
--to=michael@metaparadigm.com \
--cc=akpm@digeo.com \
--cc=andrea@suse.de \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox