[Top] [All Lists]

Re: xfs lockup on 2.4.6-SMP kernel with 1.1TB filesystem

To: Jani Jaakkola <jjaakkol@xxxxxxxxxxxxxx>
Subject: Re: xfs lockup on 2.4.6-SMP kernel with 1.1TB filesystem
From: Simon Matter <simon.matter@xxxxxxxxxxxxxxxx>
Date: Wed, 18 Jul 2001 08:29:17 +0200
>received: from mobile.sauter-bc.com (unknown []) by basel1.sauter-bc.com (Postfix) with ESMTP id 297C157306; Wed, 18 Jul 2001 08:38:55 +0200 (CEST)
Cc: linux-xfs@xxxxxxxxxxx
Organization: Sauter AG, Basel
References: <Pine.LNX.4.33.0107172140000.14439-100000@xxxxxxxxxxxxxxxxxxxxxx>
Sender: owner-linux-xfs@xxxxxxxxxxx
Jani Jaakkola schrieb:
> On Tue, 17 Jul 2001, Steve Lord wrote:
> > > Right, it has now been running longer than ever before without a lockup.
> > > However, the performance is very bad. But it just might be caused by the
> > > simultaneous RAID resync I am doing at the same time. I'll get back to
> > > this after the resync is done (or the machine has crashed).
> >
> > Yes, the resync will crucify performance until it is complete. I think you
> > can control the rate it runs at - I would get it out of the way as soon
> > as possible, I think it has nasty cache invalidation effects when running
> > with XFS.
> Does that mean, that XFS could have problems with SW RAID rebuild
> after a disk failure? After I get things running, I'm going to test what
> happens when I remove a disk from hotswap and plug it back again in live
> system. I need to have that working before putting the system to use (even
> if it requires to spend some $$ on some RAID hardware).
> - Jani

I did use
sysctrl -w dev.raid.speed_limit_min=10000
to speed up RAID5 resync and I was afraid it could give me a problem but
it did not. Whe forcing higher speed it does really slow down the system
but I have never been able to produce an error.
BTW: Is the RAID code in linus kernels the same like in RH kernels?
I was using the RH-XFS 2.4.3-1.0.1 release.

<Prev in Thread] Current Thread [Next in Thread>