On Wed, Nov 26, 2014 at 6:55 AM, Martijn Dekkers <martijn@xxxxxxxxxxxxxx> wrote:
>
> [ ... ]
>
> Whilst this looks like an OCFS2 issue, I am posting this here as I have seen
> some bugs in the Ceph tracker with similar patterns: ceph socket closed,
> combined with [TASK] blocked for more than 120 seconds.
>
> I would appreciate any pointers as to where to even begin looking for
> resolving this issue. besides the random "host rebooting" there is also a
> question of performance, but I am testing the various independent components
> to figure out where the bottlenecks are.
Try monitoring the contents of /sys/kernel/debug/ceph/*/osdc when you
see these blocked task splats. It should tell us if there are any
outstanding rbd requests that the system can be waiting on.
Thanks,
Ilya
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
