In this paper we present the results of analyzing different approaches to implementing dynamic allocation on a large space-shared Linux cluster using an actual historical workload. We take the approach that dynamic allocation of nodes to processes can be initiated by the application as opposed to the more commonly studied approach in which the operating system requests an application to change the number of nodes it is allocated. We take the stance that jobs requesting dynamic allocation should have a minimized impact on the rest of the system. We conclude that this occurs when dynamic allocation is implemented in a non-blocking, non-priority fashion. We give a proposal for an implementation of dynamic allocation under MPI-2 which is non-priority and gives the user the choice of blocking and non-blocking while waiting for additional nodes.