Characterization of server performance bottlenecks in distributed interactive simulation environments

Servers running distributed simulation applications need to process a large number of small packets at the network level. This becomes a burden on the server CPUs and exhibits itself as high CPU utilization. In this paper, first, we confirm this phenomenon, then, we utilize performance analyzer tools from major processor vendors to characterize the major sources of CPU usage. In addition, the experiments run on real hardware reveal server bottlenecks within the context of new architectural features such as hyper-threading, hyper-transport and multi-core processors.