* Some weirdness with slub in 3.0-rc*
@ 2011-06-17 20:30 Josef Bacik
2011-06-17 20:41 ` Christoph Lameter
0 siblings, 1 reply; 2+ messages in thread
From: Josef Bacik @ 2011-06-17 20:30 UTC (permalink / raw)
To: cl; +Cc: penberg, mpm, linux-mm
Hello,
I started noticing that when I rmmod'ed btrfs after running a stress
test on it that it would complain about objects still left on a couple
of it's slab's. I git bisect'ed it but it wasn't coming out right, and
I just ran the test again with slab instead of slub and it works out
fine. Does this sound familiar to anyone? I can try and bisect it
down, but the test takes like 30 minutes to reproduce (thankfully I can
reproduce this every time), so it's going to take a little bit if it
doesn't ring anybodies bells. Thanks,
Josef
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: Some weirdness with slub in 3.0-rc*
2011-06-17 20:30 Some weirdness with slub in 3.0-rc* Josef Bacik
@ 2011-06-17 20:41 ` Christoph Lameter
0 siblings, 0 replies; 2+ messages in thread
From: Christoph Lameter @ 2011-06-17 20:41 UTC (permalink / raw)
To: Josef Bacik; +Cc: penberg, mpm, linux-mm
On Fri, 17 Jun 2011, Josef Bacik wrote:
> I started noticing that when I rmmod'ed btrfs after running a stress
> test on it that it would complain about objects still left on a couple
> of it's slab's. I git bisect'ed it but it wasn't coming out right, and
> I just ran the test again with slab instead of slub and it works out
> fine. Does this sound familiar to anyone? I can try and bisect it
> down, but the test takes like 30 minutes to reproduce (thankfully I can
> reproduce this every time), so it's going to take a little bit if it
> doesn't ring anybodies bells. Thanks,
No does not sound familiar. If its some sort of sporadic issue then its
difficult to establish causation. Slub logs information about the objects
to the syslog. Could you post the output? The output will be more detailed
if you run with slub debugging on (pass slub_debug on the kernel command
line).
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2011-06-17 20:41 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2011-06-17 20:30 Some weirdness with slub in 3.0-rc* Josef Bacik
2011-06-17 20:41 ` Christoph Lameter
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox