Re: OSD deadlock with cephfs client and OSD on same machine

[Amon Ott <a.ott@m-privacy.de>]

On Wednesday 30 May 2012 wrote Amon Ott:
> On Tuesday 29 May 2012 you wrote:
> > On Tue, 29 May 2012, Amon Ott wrote:
> > > Please consider putting out a fat warning at least at build time, if
> > > syncfs() is not available, e.g. "No syncfs() syscall, please expect a
> > > deadlock when running osd on non-btrfs together with a local cephfs
> > > mount." Even better would be a quick runtime test for missing syncfs()
> > > and storage on non-btrfs that spits out a warning, if deadlock is
> > > possible.
> >
> > I think a runtime warning makes more sense; nobody will see the build
> > time warning (e.g., those installed debs).
>
> Yes, fully agreed.

Thanks for the new log lines in master git. The warning without syncfs() 
support could be a bit more clear though - the system is not only slower, it 
hangs needing a reset and reboot. This is much worse, specially if cephfs is 
permanently broken by bug 1047 afterwards. And I am pretty sure that our 
systems were not running out of memory, because during our load tests we 
always have several GB of unused memory.

After backporting syncfs() support into Debian stable libc6 2.11 and 
recompiling Ceph with it, our test cluster is now running with syncfs().

A first two hour load test this morning did not produce any problems, so I can 
say that syncfs() makes it significantly more stable than sync(). We will 
make a several day load test soon.

Amon Ott
-- 
Dr. Amon Ott
m-privacy GmbH           Tel: +49 30 24342334
Am Köllnischen Park 1    Fax: +49 30 24342336
10179 Berlin             http://www.m-privacy.de

Amtsgericht Charlottenburg, HRB 84946

Geschäftsführer:
 Dipl.-Kfm. Holger Maczkowsky,
 Roman Maczkowsky

GnuPG-Key-ID: 0x2DD3A649
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html