On 09/07/2013 14:57, Mikaël Cluseau wrote:
I think I'll go for the second option because the problematic load spikes seem to have a period of 24h + epsilon...
Seems good : the load drop behind the 1.0 line, ceph starts to scrub, the scrub is fast and load goes higher the 1.0, there's a pause, and it starts again :)
Good evening! :) _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
