previously excluded all parttions that overlapped with one that had pending jobs that needed
    resources.
now exclude only partitions that are a superset of the partition with pending jobs

has been satisfied.

    to zero (possibly changing a pending job's resource requirements from a 
    processor on some node to the full node).

the node list, count of allocated nodes, and number of processors allocated per node 

added suspend time to the table along with flushing jobs at cold start.  Suspend time isn't calculated yet, but we will figure it out