<snip>
But I keep coming back to the same question. If the goal of this project is putting together grid of clients using open technology, will this grid be explicitly made up solely of Fedora clients? Will the cpu cycles be directed for Fedora internal needs or for generally interesting computational problems? Once the technology is built and accessible your SIG will end up having to craft some policy concerning how grid tasking will be handled.
I don't think we need to limit this to Fedora clients as Condor supports clients across a variety of platforms. But, I would expect that if we can make the clients a part of a standard Fedora distribution, we would have substantially more Fedora clients than other platforms. Also, it may be useful to start with Fedora in the beginning to keep the scope of the work smaller and manageable.
I think we should start with Fedora infrastructure needs and then expand to other computational problems. Getting it right first for Fedora will give us a good foundation for adding other projects.
Bryan _______________________________________________ fedora-advisory-board mailing list fedora-advisory-board@xxxxxxxxxx http://www.redhat.com/mailman/listinfo/fedora-advisory-board
