public inbox for linux-xfs@vger.kernel.org
 help / color / mirror / Atom feed
* reservation ran out?
@ 2009-09-05 16:11 Gavin Peters
  2009-09-06  4:03 ` Eric Sandeen
  0 siblings, 1 reply; 3+ messages in thread
From: Gavin Peters @ 2009-09-05 16:11 UTC (permalink / raw)
  To: xfs

I just created bug 849, about a reservation problem I'm seeing
on my x86_64 system on ubuntu jaunty (2.6.28-15-generic).

http://oss.sgi.com/bugzilla/show_bug.cgi?id=849

Am I doin' something wrong, or is this a real problem?

- Gavin

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: reservation ran out?
  2009-09-05 16:11 reservation ran out? Gavin Peters
@ 2009-09-06  4:03 ` Eric Sandeen
  2009-09-06 12:17   ` Gavin Peters
  0 siblings, 1 reply; 3+ messages in thread
From: Eric Sandeen @ 2009-09-06  4:03 UTC (permalink / raw)
  To: Gavin Peters; +Cc: xfs

Gavin Peters wrote:
> I just created bug 849, about a reservation problem I'm seeing
> on my x86_64 system on ubuntu jaunty (2.6.28-15-generic).
> 
> http://oss.sgi.com/bugzilla/show_bug.cgi?id=849
> 
> Am I doin' something wrong, or is this a real problem?

Sounds like a real problem.

Any reproducible testcase?

-Eric

> - Gavin

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: reservation ran out?
  2009-09-06  4:03 ` Eric Sandeen
@ 2009-09-06 12:17   ` Gavin Peters
  0 siblings, 0 replies; 3+ messages in thread
From: Gavin Peters @ 2009-09-06 12:17 UTC (permalink / raw)
  To: Eric Sandeen; +Cc: Gavin Peters, xfs


On Sat, Sep 05, 2009 at 11:03:54PM -0500, Eric Sandeen wrote:
> Gavin Peters wrote:
>> I just created bug 849, about a reservation problem I'm seeing
>> on my x86_64 system on ubuntu jaunty (2.6.28-15-generic).
>>
>> http://oss.sgi.com/bugzilla/show_bug.cgi?id=849
>>
>> Am I doin' something wrong, or is this a real problem?
>
> Sounds like a real problem.
>
> Any reproducible testcase?
>

Alas, no; I was running mythtv, and my disk was somewhat fragmented.

root@mythmaker:~# xfs_db -c frag -r /dev/sda7
actual 17379, ideal 98, fragmentation factor 99.44%
root@mythmaker:~# xfs_db -c frag -r /dev/sdb1
actual 4268, ideal 53, fragmentation factor 98.76%

The disk that was having the trouble was sda7, my sdb1 was fine.  

Mythtv fragments disks so badly by appending to two, or three files,
simultaniously and fsyncing on them a lot.  Perhaps some hacking at
that will give a reproduction, I'll see if I can take the time and do
that.

I've since defragmented both disks though; and I've set a large
allocsize (512m) to prevent future fragmentation.  We'll see if I get
another crash.

- Gavin

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2009-09-06 12:16 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2009-09-05 16:11 reservation ran out? Gavin Peters
2009-09-06  4:03 ` Eric Sandeen
2009-09-06 12:17   ` Gavin Peters

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox