On Wed, 11 Mar 2015, Stefan Priebe - Profihost AG wrote: > Hi Sage, > Am 11.03.2015 um 04:14 schrieb Sage Weil: > > On Wed, 11 Mar 2015, Christian Balzer wrote: > >> On Tue, 10 Mar 2015 12:34:14 -0700 (PDT) Sage Weil wrote: > >> > >> > >>> Adjusting CRUSH maps > >>> -------------------- > >>> > >>> * This point release fixes several issues with CRUSH that trigger > >>> excessive data migration when adjusting OSD weights. These are most > >>> obvious when a very small weight change (e.g., a change from 0 to > >>> .01) triggers a large amount of movement, but the same set of bugs > >>> can also lead to excessive (though less noticeable) movement in > >>> other cases. > >>> > >>> However, because the bug may already have affected your cluster, > >>> fixing it may trigger movement *back* to the more correct location. > >>> For this reason, you must manually opt-in to the fixed behavior. > >>> > >> It would be nice to know at what version of Ceph those bugs were > >> introduced. > > > > This bug has been present in CRUSH since the beginning. > > So peaople upgrading from dumplang have todo the same? > > 1.) They need to set tunables to optimal (to get firefly tunables) > 2.) They have to set those options you mention? Nothing has to (or probably should be) done as part of the upgrade process itself. This tunable can be set without changing to firefly tunables. It affects the monitor-side generation of internal weight values one, and has no dependency or compatibility issue with clients or OSDs. And the bug only triggers when a weight is changed. sage _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |