Hum. We see scattered reports of this occasionally (although it seems to clump), but usually it's on self-built distros. It's not behavior we've encountered on any regular basis and it's not expected. If you're getting all your packages from Canonical, you should probably report the bug to them as well — it might be a tcmalloc issue they can resolve in their repo. -Greg Software Engineer #42 @ http://inktank.com | http://ceph.com On Mon, Apr 14, 2014 at 7:04 AM, David McBride <dwm37@xxxxxxxxx> wrote: > On 14/04/14 14:53, Gregory Farnum wrote: >> What distro are you running on? >> -Greg > > Hi Greg, > > This is sitting atop a pre-release build of Ubuntu 14.04, using the > packages provided by same. > > dpkg-query -W ceph shows: > > ceph 0.79-0ubuntu1 > > ceph --version shows: > > ceph version 0.79 (4c2d73a5095f527c3a2168deb5fa54b3c8991a6e) > > Note that I'm currently half-way through nuking my existing cluster (to > reduce my PG count, and experiment with different OSD filesystems); I'm > happy to run experiments, but there'll be a small lag while I bring the > cluster back up! > > Cheers, > David > -- > David McBride <dwm37@xxxxxxxxx> > Unix Specialist, University Information Services -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
