Ugis:
2015-06-06 08:03:31.770812 7fe5002c2700 0 log_channel(default) log
[WRN] : slow request 30720.717642 seconds old, received at 2015-06-05
23:31:31.032740: osd_op(client.2457394.0:8430
In our experience blocked requests that long have been the cause of cluster freeze several times. See this thread for details:
http://lists.ceph.com/pipermail/ceph-users-ceph.com/2015-May/001656.html
http://lists.ceph.com/pipermail/ceph-users-ceph.com/2015-May/001656.html
You should check that OSD logs to find out why the slow requests are happening. In any case you'll probably need to restart all OSD with blocked requests or even take them all out, wait until the cluster gets health ok back, and then to put them in again.
(BTW, I'm removing ceph-devel from Cc because I'm not subscribed to that list.)
Cheers,
Alex
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
