hi to all here
we tried a lot and now, we need your help ...
we are using 5 proxmox 7.2-3 server with kernel 5.15.30-2-pve and ceph
16.2.7..
per server, we use 9 osd (8x 2tb, 1x8tb both sas ssd, connected via sas
hba)
the second cluster for replication is the same hardware.
at first, we tried was journal mode.
everything was fine, but the used disk space in the cluster was growing
(nearly 700gb per day).
entries_behind_primary were looking good, some images with a value of
300, most 1-3.
after that, we switched to snapshot based.
also ... everything was working fine (50 days), up to last week.
since last week, we see a high i/o load in our virtual machines (kvm).
we tried a lot, but did not find anything.
the hardware, proxmox and kvms were not modified.
after disabling the snapshot feature on the rbd images, the load goes
down.
disabling the rbd mirror processes did not help, load stays up.
now we went back to journal, but the pool size is growing again.
does anybody use rbd mirroring?
which type are you using? what would you prefer?
we are running against walls ... so any help is welcome.
kind regards,
ronny.lippold
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
