Network analysis of Counter-strike and Starcraft

Network games are becoming increasingly popular, but their traf ic patterns have received little attention from the academic research community. A better understanding of network game t ra f i c can lead t o more effective network architectures and more realistic network simulations. W e gathered t ra f i c traces from live Internet games of Counter-strike and Starcraft, representative games from two different gaming genres. In this paper, we analyzed the network traf ic patterns and bandwidth consumption t o better understand how such games impact the network. Bo th games were found t o have very low bandwidth usage and packets significantly smaller than typical Internet applications. Starcraft games showed consistent trafic behavior across games while the traf ic patterns f o r Counter-strike varied widely, especially f o r the server. In particular, Counter-strike clients and servers often send bursts of very small packets. Since current Internet routers are typically designed f o r large transfers with large packets, there m a y be opportunities to improve network architectures t o better manage and support game traf ic .