Hi all, we have a 5 node ceph cluster with 44 OSDs where all nodes also serve as virtualization hosts, running about 22 virtual machines with all in all about 75 rbd s (158 including snapshots). We experience absurd slow i/o in the VMs and I suspect our thread settings in ceph.conf to be one of the culprits. Is there a rule of thumb how to get the proper setting? What side effect will have a higher threads setting? Higer cpu utilisation? higher memory impact? TIA _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |