Search results

Hey, i don´t think it´s somewhere "documented". It´s more in the nature ceph allocates space in objects in placement groups. You can have a full cluster with lot of osds only at 80% and only one or a few osd at 95% or so. Then your cluster is observed as "full". Free = 0. And if you rebalance...

I think the "total space" is a sum up from ceph available space. That is - as i understand - not totally fixed, because of the fill-grade of each single osd and the possibility to place new data regarding the crush algo.

Hey, maybe you missed the "wiping your disk" part from Dominics answer. I never had problems with seeing disks. Wiping the disk (search for zap) depends on your actual versions, if you already use ceph-volume or the "old" ceph disk tools. Be careful not to use wrong device strings.

Hey, hatte das schon mal in Verbindung mit ZFS und swap. Ursache für hängendes df -h / qm list etc. ist bei uns immer ein Process im D state gewesen. Manchmal hilft da ein einfaches "systemctl restart pve-cluster". Ob das in diesem Fall a) gefahrlos möglich ist und b) auch hilft, kann ich...