slow ops of osds

Hello Forum! I run a 3 nodes hyper-converged meshed 10GbE ceph cluster, currently updated to the latest version on 3 identical hp server as a test-environment (pve 6.3.3 and ceph octopus 15.28, no HA,) with 3 x 16 SAS-HDs connected via HBA, 3x pve-os + 45 osds, rbd only, activated...