2012/1/5 Chris Mason [off-list ref]:

On Fri, Jan 06, 2012 at 07:12:16AM +1100, Dave Chinner wrote:

quoted

On Thu, Jan 05, 2012 at 02:45:00PM -0500, Chris Mason wrote:

quoted

On Thu, Jan 05, 2012 at 01:46:57PM -0500, Chris Mason wrote:

quoted

On Thu, Jan 05, 2012 at 10:01:22AM +1100, Dave Chinner wrote:

quoted

On Thu, Jan 05, 2012 at 09:23:52AM +1100, Chris Samuel wrote:

quoted

On 05/01/12 09:11, Dave Chinner wrote:

quoted

Looks to be reproducable.

Does this happen with rc6 ?

I haven't tried. All I'm doing is running some benchmarks to g=

et

quoted

quoted

quoted

quoted

numbers for a talk I'm giving about improvements in XFS metada=

ta

quoted

quoted

quoted

quoted

scalability, so I wanted to update my last set of numbers from
2.6.39.

As it was, these benchmarks also failed on btrfs with oopsen a=

nd

quoted

quoted

quoted

quoted

corruptions back in 2.6.39 time frame. =A0e.g. same VM, same
test, different crashes, similar slowdowns as reported here:
http://comments.gmane.org/gmane.comp.file-systems.btrfs/11062

Given that there is now a history of this simple test uncoveri=

ng

quoted

quoted

quoted

quoted

problems, perhaps this is a test that should be run more regul=

arly

quoted

quoted

quoted

quoted

by btrfs developers?

Unfortunately, this one works for me. =A0I'll try it again and s=

ee if I

quoted

quoted

quoted

can push harder. =A0If not, I'll see if I can trade beer for som=

e

quoted

quoted

quoted

diagnostic runs.

Aha, if I try it just on the ssd instead of on my full array it tr=

iggers

quoted

quoted

at 88M files. =A0Great.

Good to know. =A0The error that is generating the BUG on my machine =

is

quoted

-28 (ENOSPC). =A0Given there's 17TB free on my filesystem....

Yeah, same thing here. =A0I'm testing a fix now, it's pretty dumb. =A0=

We're

not allocating more metadata chunks from the drive because of where t=

he

allocation is happening, so it is just a check for "do we need a new
chunk" in the right place.

I'll make sure it can fill my ssd and then send to you.

Could you send the patch to the list (or to me), please? Telling from
what you mentioned on IRC this sounds quite interesting and I would
like to see if this solves my performance problems with ceph, too...

Thanks,
Christian
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" =
in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html