[one-users] Copy image on Ceph to file-based datastore

Jaime Melis jmelis at opennebula.org
Tue Mar 18 02:26:35 PDT 2014


Hi Stuart,

before moving on to the implementation details, how are you thinking of
specifying if a VM should run from the datastore or from a local file?

I'm afraid this is going to be very tricky, because we need to figure out
how to tell the core to generate a deployment file that references a local
file and not a ceph disk [1]

We want the 'if' to go this way:
https://github.com/OpenNebula/one/blob/master/src/vmm/LibVirtDriverKVM.cc#L502
and not this one:
https://github.com/OpenNebula/one/blob/master/src/vmm/LibVirtDriverKVM.cc#L445



On Thu, Mar 13, 2014 at 8:47 AM, Stuart Longland <stuartl at vrt.com.au> wrote:

> Hi all,
>
> In OpenNebula, it seems we can easily set it up to use Ceph as a
> datastore for images, cloning non-persistent images to make temporary
> copies, etc.
>
> We can also have the images stored as files on the frontend computer and
> dolled out via SSH; and in the case of "persistent" images, copied back
> when the VM is undeployed.
>
> What I'm missing is a hybrid between the two.  We've got a 3-node Ceph
> cluster which is working well.  However, compared to a local SSD, the
> Ceph cluster with its 6 spinners is a bit on the slow side in comparison.
>
> There are VMs for which we don't care about resiliency, and so it makes
> sense to use the SSDs attached to the VM hosts, and store the image
> itself in Ceph.
>
> The thought is, when the VM starts up, rather than having it dished out
> from the frontend computer, the host does a:
>
>         rbd export pool-name/image-name
> /var/lib/one/datastores/123/45/disk.0
>
> Then, if the image is "persistent", it does a
>
>         rbd import pool-name/image-name
> /var/lib/one/datastores/123/45/disk.0
>
> (Note: not sure if import will "overwrite" the image, it may be
> necessary to do a rbd rm first of the old image... or better, import the
> new copy then remove and rename.)
>
> I had a tinker looking at the ssh transfer driver, but couldn't quite
> figure out how to reach out to the other datastore without some ugly
> kludges.
>
> Anyone else done somthing like this?
>
> Regards,
> --
> Stuart Longland
> Systems Engineer
>      _ ___
> \  /|_) |                           T: +61 7 3535 9619
>  \/ | \ |     38b Douglas Street    F: +61 7 3535 9699
>    SYSTEMS    Milton QLD 4064       http://www.vrt.com.au
>
>
> _______________________________________________
> Users mailing list
> Users at lists.opennebula.org
> http://lists.opennebula.org/listinfo.cgi/users-opennebula.org
>



-- 
Jaime Melis
Project Engineer
OpenNebula - Flexible Enterprise Cloud Made Simple
www.OpenNebula.org | jmelis at opennebula.org
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.opennebula.org/pipermail/users-opennebula.org/attachments/20140318/1b079cc3/attachment-0002.htm>


More information about the Users mailing list