See below:

On Aug 27, 2020, at 3:19 PM, info--- via Users <users@ovirt.org> wrote:

Thank you. Reboot of the engine and afterwards the backup server helped :-)

Good deal.

Should I revert some of my previous changes? Reduce the write window size?
- gluster volume set vmstore performance.read-ahead on
- gluster volume set vmstore performance.stat-prefetch on
- gluster volume set vmstore performance.write-behind-window-size 64MB
- gluster volume set vmstore performance.flush-behind on
- gluster volume set vmstore cluster.choose-local on

I find these tend to be workload & system dependent, you’re best bet is to benchmark and test yourself on your system.

I’m using these on my volumes:
performance.stat-prefetch: on
performance.read-ahead: off
performance.write-behind-window-size: 64MB