Hi, This is regarding something I already posted on ask openstack, without getting an answer (https://ask.openstack.org/en/question/69443/glance-performances-when-uploading-snapshots-to-a-ceph-backend/). Basically, we notice that when uploading to our image storage backend, the glance process seems limited to using 30% of a cpu core. The network upload is limited to 80 MB/sec, despite a 10gbps link. If I start several glances upload, the processes stack. It is only possible to reach my hardware and network limit if I stack a high enough number of processes. Is there a way to control this behavior? Best regards, -- ====================== Jean-Philippe Méthot Administrateur système / System administrator GloboTech Communications Phone: 1-514-907-0050 Toll Free: 1-(888)-GTCOMM1 Fax: 1-(514)-907-0750 jpmethot at gtcomm.net http://www.gtcomm.net