On Wed, Jul 3, 2019 at 4:47 PM Luk <skidoo@xxxxxxx> wrote:
this pool is that 'big' :
[root@ceph-mon-01 ~]# rados df | grep -e index -e WR
POOL_NAME USED OBJECTS CLONES COPIES MISSING_ON_PRIMARY UNFOUND DEGRADED RD_OPS RD WR_OPS WR
default.rgw.buckets.index 0B 31763 0 95289 0 0 0 147679875 3.88TiB 8014040021 0B
You are running Luminous which doesn't account metadata properly here. 31763 objects in an an rgw index pool is a non-trivial size.
However, scrubbing that shouldn't be a problem for a properly configured cluster (i.e., no gigantic shards). Have you tried to increase osd_scrub_sleep?
--
Paul Emmerich
Looking for help with your Ceph cluster? Contact us at https://croit.io
croit GmbH
Freseniusstr. 31h
81247 München
www.croit.io
Tel: +49 89 1896585 90
Paul Emmerich
Looking for help with your Ceph cluster? Contact us at https://croit.io
croit GmbH
Freseniusstr. 31h
81247 München
www.croit.io
Tel: +49 89 1896585 90
[root@ceph-mon-01 ~]# ceph df | grep -e index -e N
NAME ID USED %USED MAX AVAIL OBJECTS
default.rgw.buckets.index 20 0B 0 37.0TiB 31763
[root@ceph-mon-01 ~]#
I don't think it should have such big problem during scrubing...
--
Regards
Lukasz
_______________________________________________
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
