First question: why do you want to do this? There are some deployment scenarios in which moving the drives will Just Work, and others in which it won’t. If you try, I suggest shutting the system down all the way, exchanging just two drives, then powering back on — and see if all is well before doing all. On which Ceph release were these OSDs deployed? Containerized? Are you using ceph-disk or ceph-volume? LVM? Colocated journal/DB/WAL, or on a seperate device? Try `ls -l /var/lib/ceph/someosd` or whatever you have, look for symlinks that reference device paths that may be stale if drives are swapped. > > Hello, > > Have I check same global flag for this operation? > > Thanks! > ________________________________ > De: Stefan Kooman <stefan@xxxxxx> > Enviado: miércoles, 18 de mayo de 2022 14:13 > Para: Jorge JP <jorgejp@xxxxxxxxxx> > Asunto: Re: Best way to change disk in controller disk without affect cluster > > On 5/18/22 13:06, Jorge JP wrote: >> Hello! >> >> I have a cluster ceph with 6 nodes with 6 HDD disks in each one. The status of my cluster is OK and the pool 45.25% (95.55 TB of 211.14 TB). I don't have any problem. >> >> I want change the position of a various disks in the disk controller of some nodes and I don't know what is the way. >> >> - Stop osd and move the disk of position (hotplug). >> >> - Reweight osd to 0 and move the pgs to other osds, stop osd and change position >> >> I think first option is ok, the data not deleted and when I will changed the disk the server recognised again and I will can start osd without problems. > > Order of the disks should not matter. First option is fine. > > Gr. Stefan > _______________________________________________ > ceph-users mailing list -- ceph-users@xxxxxxx > To unsubscribe send an email to ceph-users-leave@xxxxxxx _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |