After some manual rebalancing, all PGs went into a clean state and I was abler to start the balancer again. ¯\_(ツ)_/¯ > Am 14.12.2022 um 01:18 schrieb Boris Behrens <bb@xxxxxxxxx>: > > Hi, > we had an issue with an old cluster, where we put disks from one host > to another. > We destroyed the disks and added them as new OSDs, but since then the > mgr daemon were restarting in 120s intervals. > > I tried to debug it a bit, and it looks like the balancer is the problem. > I tried to disable it and create a plan on my own, but then the active > manager just stops and the failover takes place. > > Any idea how to easily fix it or debug it further? > > I am currently trying to resolve the backfillfull issue by hand (ceph > osd reweight) and then to restart all OSD hosts. > > -- > Die Selbsthilfegruppe "UTF-8-Probleme" trifft sich diesmal abweichend > im groüen Saal. _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |