I've got processes that need to be farmed out over a cluster that supports PBS, however, due to limitations with the process, I can only run one process per node at a time. Each node has two processors, the ghetto approach would be to simply request two processors per job. But that wastes a core per job. Is it possible to request a single core per job while making sure that only a single process from all of my jobs is running at a time on a given node?