It shouldn't be -- if you changed pg_num then a bunch of PGs will need to move and will report in this state. We can check more thoroughly if you provide the full "Ceph -s" output. (Stuff to check for: that all PGs are active, none are degraded, etc) -Greg
On Wednesday, November 4, 2015, Erming Pei <[email protected]> wrote: > Hi, > > I found that the pg_num and pgp_num for meta data pool was too small and > then increased them. > Then I got "300 pgs stuck unclean". > > > > > * $ ceph -s cluster a4d0879f-abdc-4f9d-8a4b-53ce57d822f1 health > HEALTH_WARN 248 pgs backfill; 52 pgs backfilling; 300 pgs stuck unclean; > recovery 58417161/113290060 objects misplaced (51.564%); mds0: Client > physics-007:Physics01_data failing to respond to cache pressure * > Is it critical? > > thanks, > > Erming > > > > > > -- > --------------------------------------------- > Erming Pei, Ph.D > Senior System Analyst; Grid/Cloud Specialist > > Research Computing Group > Information Services & Technology > University of Alberta, Canada > > Tel: +1 7804929914 Fax: +1 7804921729 > --------------------------------------------- > >
_______________________________________________ ceph-users mailing list [email protected] http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
