Hi Sam, Andrew, as Alexander and Alexis in the other branch of this thread (about scheduling), I just wanted to make sure that other OGF groups and standards get considered, and involved, *when appropriate*. So I'm happy to hear that people have considered to use GLUE, and that GLUE MAY be usable as alternative representation, etc. Quoting [Sam Johnston] (Apr 14 2009):
Further to Andrew's comments, I've thus far tried to avoid fixed schemas for anything, preferring tags and attributes and deferring a lot of that detail to supporting standards like OVF. I don't see a problem with using GLUE as an "alternate" representation and/or linking to it using <link>s or an extension. I hope that answers your question... basically I suggest that we [re]use it if we need to but not before. Sam
On Tue, Apr 14, 2009 at 2:36 PM, Edmonds, AndrewX <[1]andrewx.edmonds@intel.com> wrote:
Hey Andre - we reviewed GLUE in SLA@SOI to see if it would meet our needs for infrastructure provisioning but for the most our initial feelings are that it wouldn't suit. Would you have any other viewpoint on this? Andy
Andrew, would you be able to feed back to the GLUE WG where you considered the standarde to fall short of your requirements? They might be interested to learn about that.
But anyway: do you expect GLUE to play any role in respect to the specification of (VM) resource requirements?
I am actually not familiar enough with the topic to really have an educated opinion. As an observer, it seems that the OCCI will need to touch resource description at some point or the other, to specify requirements to a VM for example, and GLUE seems to aim at that type of use case. Not sure if any from the GLUE people are listening here. If not, it might be worthewhile to get their feedback at next OGF, by going to their session... Cheers, Andre. -- Nothing is ever easy.