Hello, I have a NAS box used by two KVM hypervisors[1] over NFS. The NAS box has two Gigabit ethernet and several TB of storage. The two hypervisors have their OS on SSD and a local 500GB 10k SATA drive. As we had performance issues, our setup creates a new qcow2 image on the local disk using the ?backing store? option pointing to the qcow2 image stored on NFS. I'm wondering if gluster could not have better performances than NFS and if there is a possibility to use the local 10k SATA disk as some kind of cache. I see 3.6 has heterogeneous bricks size support[2], but is there a way to have at least a copy of all the qcow2 images on my NAS box and using the local disk to improve performance? Regards. Footnotes: [1] http://opennebula.org/ [2] https://github.com/gluster/glusterfs/blob/release-3.6/doc/release-notes/3.6.0.md#better-support-for-bricks-with-heterogeneous-sizes -- Daniel Dehennin R?cup?rer ma clef GPG: gpg --recv-keys 0xCC1E9E5B7A6FE2DF Fingerprint: 3E69 014E 5C23 50E8 9ED6 2AAD CC1E 9E5B 7A6F E2DF -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 342 bytes Desc: not available URL: <http://www.gluster.org/pipermail/gluster-users/attachments/20150118/a3f13d84/attachment.sig>