Multicast grouping for data distribution management

Abstract

The High Level Architecture's (HLA) Data Distribution Management (DDM) services are the most recent in a succession of systems designed to reduce the amount of data received by individual simulations in large-scale distributed simulations. A common optimization in these interest management systems is the use of multicast groups for sending data to a selected subset of all potential receivers. The use of multicast has met with considerable success in this application. However, its use to date has relied on a priori knowledge of communication patterns between simulations and static assignment of multicast groups to these patterns. As larger, more complex, and less predictable simulations are built, the need has arisen for more efficient use of multicast groups as they are a restricted resource [3Com Corporation, Scaling Performance and Managing Growth with the CoreBuilder 3500 Layer 3 Switch (available at http://www.3com.com/products/dsheets/400347a.html) lists a limit of 6 K, the highest number identified while Synthetic Theater of War (STOW) (D. Van Hook, RITN IM and IM history, personal communication, January 1996) had a hardware limit of approximately 1000. A typical workstation network interface card has only a few (H. Abrams, Extensible interest management for scalable persistent distributed virtual environments, Ph.D. Dissertation, Naval Postgraduate School, December 1999)]. This paper presents two algorithms for performing grouping, and the message delivery time improvements resulting from applying the algorithms to selected data sets.