On Mon, 29 Apr 2019, Alexander Y. Fomichev wrote: > Hi, > > I just upgraded from mimic to nautilus(14.2.0) and stumbled upon a strange > "feature". > I tried to increase pg_num for a pool. There was no errors but also no > visible effect: > > # ceph osd pool get foo_pool01 pg_num > pg_num: 256 > # ceph osd pool set foo_pool01 pg_num 512 > set pool 11 pg_num to 512 > # ceph osd pool get foo_pool01 pg_num > pg_num: 256 > > until finally I found that > # ceph osd require-osd-release nautilus > solves this problem > > Docs are very scarce about "require-osd-release" command. Something like > "Complete the upgrade by disallowing pre-Nautilus OSDs and enabling all new > Nautilus-only functionality:" which gives no clue to understand why pretty > old feature of increasing pg_num dosn't work. Any way I doubt that silently > ignoring user commands is a good idea. > So question is: It is intentional behavior or I hit a bug. You hit a bug. :) Starting in nautilus, the pg_num and pgp_num adjustments are managed by the manager. When you make a change on the CLI, you're setting the pgp_num_target value, and the mgr makes the real changes in a managed/careful way. In this case, the mon was assuming the nautilus behavior and then effectively discarding it because the osdmaps are still encoded in the mimic format. Opened http://tracker.ceph.com/issues/39570 sage _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |