Using LVM on top of a RBD.

[Daniel Hoffman <daniel@xxxxxxxxxx>]

Hi All.

I have a legacy server farm made up of 7 nodes running KVM and using LVM(LVs) for the disks of the virtual machines. The nodes at this time are CentOS 6.

We would love to remove this small farm from our network and use CephRBD over using a traditional iSCSI block device as we currently do.

Has anyone run into issues with Ceph.RBD and LVM ontop? I would almost thing this is semi redundant as most Linux distro's run LVM's by default now so any RBD being used would probably have LVM on it.

The system does daily snapshot, copy out (dd) and snapshot remove on every LV in the cluster. Any issues/performance issues anyone would think about here?

CentOS 6 shipping driver, should I look for a manual kernel upgrade/backport?

Performance issues in general with mode1 drivers?

Any feedback/thoughts would be appreciated.

Daniel

_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com