> Op 6 februari 2017 om 11:10 schreef Florent B <florent@xxxxxxxxxxx>: > > > # ceph -v > ceph version 10.2.5 (c461ee19ecbc0c5c330aca20f7392c9a00730367) > > (officiel Ceph packages for Jessie) > > > Yes I recently adjusted pg_num, but all objects were correctly rebalanced. > > Then a manually deleted some objects from this pool. A scrub should correct this for you. Wido > > > On 02/04/2017 06:31 PM, Shinobu Kinjo wrote: > > On Sun, Feb 5, 2017 at 1:15 AM, John Spray <jspray@xxxxxxxxxx> wrote: > >> On Fri, Feb 3, 2017 at 5:28 PM, Florent B <florent@xxxxxxxxxxx> wrote: > >>> Hi everyone, > >>> > >>> On a Jewel test cluster I have : > > please, `ceph -v` > > > >>> # ceph df > >>> GLOBAL: > >>> SIZE AVAIL RAW USED %RAW USED > >>> 6038G 6011G 27379M 0.44 > >>> POOLS: > >>> NAME ID USED %USED MAX AVAIL OBJECTS > >>> data 0 0 0 2986G 0 > >>> metadata 1 58955k 0 2986G 115 > >>> pve01-rbd01 5 2616M 0.09 2986G 862 > >>> cephfs01 6 15E 0 2986G -315 > >>> > >>> > >>> # rados -p cephfs01 ls > >>> 10000034339.00000000 > >>> > >>> > >>> Maybe I hit a bug ? > >> I wonder if you had recently adjusted pg_num? Those were the > >> situations where we've seen this sort of issue before. > >> > >> John > >> > >>> Flo > >>> > >>> _______________________________________________ > >>> ceph-users mailing list > >>> ceph-users@xxxxxxxxxxxxxx > >>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > >> _______________________________________________ > >> ceph-users mailing list > >> ceph-users@xxxxxxxxxxxxxx > >> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > > _______________________________________________ > ceph-users mailing list > ceph-users@xxxxxxxxxxxxxx > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |