Unfortunately, this was recently IDed as a major weakness of the current MDS rank configuration system. :/ You can follow https://tracker.ceph.com/issues/75892 which was filed to work on this. -Greg
On Tue, May 5, 2026 at 11:34 PM Robert Sander via ceph-users < [email protected]> wrote: > Hi, > > Given a cluster with multiple racks or rooms where the rack or room is > the failure domain for replicated pools. > > Given one or more CephFS volumes (filesystems) with at least one active > MDS each and a standby-replay for each active MDS. > > Each room or rack contains multiple MDS daemons (one per host). > > Is there a possibility to guarantee that the standby-replay MDS for each > active MDS does not run in the same failure domain (rack or room)? > > Because when both run in the same failure domain and that domain fails > there is no point in having a standby-replay. > > Are there any ideas on how to solve this? > > Regards > -- > Robert Sander > Linux Consultant > > Heinlein Consulting GmbH > Schwedter Str. 8/9b, 10119 Berlin > <https://www.google.com/maps/search/Schwedter+Str.+8%2F9b,+10119+Berlin?entry=gmail&source=g> > > https://www.heinlein-support.de > > Tel: +49 30 405051 - 0 > Fax: +49 30 405051 - 19 > > Amtsgericht Berlin-Charlottenburg - HRB 220009 B > Geschäftsführer: Peer Heinlein - Sitz: Berlin > _______________________________________________ > ceph-users mailing list -- [email protected] > To unsubscribe send an email to [email protected] > > _______________________________________________ ceph-users mailing list -- [email protected] To unsubscribe send an email to [email protected]
