2018-03-29 11:50 GMT+02:00 David Rabel <ra...@b1-systems.de>: > On 29.03.2018 11:43, Janne Johansson wrote: > > 2018-03-29 11:39 GMT+02:00 David Rabel <ra...@b1-systems.de>: > > > >> For example a replicated pool with size 4: Do i always have to set the > >> min_size to 3? Or is there a way to use min_size 2 and use some other > >> node as a decision maker in case of split brain? > >> > > > > min_size doesn't arbitrate decisions other than > > "can I write if there are only X visible copies?", where X needs to be > > > min_size > > to allow writes. > > > > It doesn't control any logic, it controls the risk level you want to > take. > > You are right. But with my above example: If I have min_size 2 and size > 4, and because of a network issue the 4 OSDs are split into 2 and 2, is > it possible that I have write operations on both sides and therefore > have inconsistent data? >
You always write to the primary, which in turn sends copies to the 3 others, so in the 2+2 split case, only one side can talk to the primary OSD for that pg, so writes will just happen on one side at most. -- May the most significant bit of your life be positive.
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
