This has never posed a problem in any of our clusters. I can't say if that's because we almost never have osds going out then back in, or if it's because that issue (forgetting the reweight) was fixed.
-- dan
|
_______________________________________________ Ceph-large mailing list Ceph-large@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-large-ceph.com