[Top] [All Lists]

Re: xfs_repair segfaults with ag_stride option

To: Eric Sandeen <sandeen@xxxxxxxxxxx>
Subject: Re: xfs_repair segfaults with ag_stride option
From: Tom Crane <T.Crane@xxxxxxxxxx>
Date: Mon, 6 Feb 2012 11:19:07 +0000
Cc: Christoph Hellwig <hch@xxxxxxxxxxxxx>, <xfs@xxxxxxxxxxx>, <T.Crane@xxxxxxxxxx>
In-reply-to: <4F2F6C00.5050108@xxxxxxxxxxx>
References: <4F293FCC.7010101@xxxxxxxxxx> <20120202124248.GA12107@xxxxxxxxxxxxx> <4F2F23F3.9000402@xxxxxxxxxx> <4F2F6C00.5050108@xxxxxxxxxxx>
User-agent: Thunderbird (X11/20111109)
Eric Sandeen wrote:
On 2/5/12 6:50 PM, Tom Crane wrote:
Hi Christoph,
Many thanks for the quick response and the patch. It was a big help.
I was able to repair our 60TB FS in about 30 hours. I have a couple
of questions;

(1) The steps in the progress report seem a little strange. See the
attachment. Is this expected?

(2) This may be a little out of band but I have heard second hand
reports from another sysadmin that the xfs tools which come with SLC5
(our current Linux distro) should not be relied upon and that SLC6
should be used. Our 60TB FS is significantly fragmented (~40%) and I
would very much like to run xfs_fsr on it. Given that I have built
the latest xfsprogs, is there any reason I should be afraid of
running xfs_fsr, on the FS which comes with SLC5? Unfortunately I
don't have ~60TB spare storage space elsewhere to backup the FS
before defragging. What would you advise?> Many thanks

Newer tools are fine to use on older filesystems, there should be no


issue there.

running fsr can cause an awful lot of IO, and a lot of file reorganization.
(meaning, they will get moved to new locations on disk, etc).

How bad is it, really?  How did you arrive at the 40% number?  Unless

xfs_db -c frag -r <block device>

Some users on our compute farm with large jobs (lots of I/O) find they take longer than with some of our other scratch arrays hosted on other machines. We also typically find many nfsd tasks in an uninterruptible wait state (sync_page), waiting for data to be copied in from the FS.

you see perf problems which you know you can attribute to fragmentation,
I might not worry about it.

You can also check the fragmentation of individual files with the
xfs_bmap tool.


Thanks for your advice.


Christoph Hellwig wrote:
Hi Tom,

On Wed, Feb 01, 2012 at 01:36:12PM +0000, Tom Crane wrote:
Dear XFS Support,
   I am attempting to use xfs_repair to fix a damaged FS but always
get a segfault if and only if -o ag_stride is specified. I have
tried ag_stride=2,8,16 & 32.  The FS is approx 60T. I can't find
reports of this particular problem on the mailing list archive.
Further details are;

xfs_repair version 3.1.7, recently downloaded via git repository.
uname -a
Linux store3 2.6.18-274.17.1.el5 #1 SMP Wed Jan 11 11:10:32 CET 2012
x86_64 x86_64 x86_64 GNU/Linux
Thanks for the detailed bug report.

Can you please try the attached patch?

xfs mailing list

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