[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20100417223854.GD25507@skl-net.de>
Date: Sun, 18 Apr 2010 00:38:54 +0200
From: Andre Noll <maan@...temlinux.org>
To: Eric Sandeen <sandeen@...hat.com>
Cc: Bernd Schubert <bernd.schubert@...tmail.fm>,
Andrew Vasquez <andrew.vasquez@...gic.com>,
"linux-ext4@...r.kernel.org" <linux-ext4@...r.kernel.org>,
Linux Driver <Linux-Driver@...gic.com>,
Thomas Helle <Helle@...bingen.mpg.de>
Subject: Re: ext4: (2.6.34-rc4): This should not happen!! Data will be lost
On 15:45, Eric Sandeen wrote:
> Interesting that it only happens at enospc time though - the fs would
> be sending barriers in general usage.
>
> Although, as ext4 fills, it does do more syncing/flushing to try to
> eke out that last bit of space.... hmm....
>
> Andre, just for fun, you might try mounting -o nodelalloc, fill it again,
> and see if you see the same behavior.
Will do. This will take some time though as I destroyed the fs by
writing directly to the device, so I had to recreate it and start from
scratch. I'm currently filling the new fs using a 60s device timeout as
suggested by Andrew.
> If not, you might do it again w/ defaults, and capture blktrace data, which
> I think will trace barrier requests as well.
>
> (or, maybe also try testing with -o nobarrier)
>
> I still don't think it's likely a filesystem problem but maybe you can
> pinpoint the fs behavior that triggers it.
I'll try to reproduce the problem using different timeout values and the
ext4 options you suggest. If I can find a reliable reproducer, I'll run
blktrace and post the results.
Regards
Andre
--
The only person who always got his work done by Friday was Robinson Crusoe
Download attachment "signature.asc" of type "application/pgp-signature" (190 bytes)
Powered by blists - more mailing lists