An Empirical Evaluation of TCP Performance in Online Games


A fundamental design question to ask in the development of a network game is--Which transport protocol should be used--TCP, UDP, or some other protocols? Seeking an objective answer to the choice of communication protocol for MMORPGs, we assess whether TCP, a popular choice, is suitable for MMORPGs based on empirical evidence. To the best of our knowledge, this work is the first evaluation of transport protocol performance using real-life game traces. We analyze a 1, 356-million-packet trace from ShenZhou Online, a TCP-based, commercial, mid-sized MMORPG.

Our analysis indicates that TCP is unwieldy and inappropriate for MMORPGs. This is due to four distinctive characteristics of MMORPG traffic: 1) tiny packets, 2) low packet rate, 3) application-limited traffic generation, and 4) bidirectional traffic. We show that because TCP was originally designed for unidirectional and network-limited bulk data transfers, it cannot adapt well to MMORPG traffic. In particular, the window-based congestion control and the fast retransmit algorithm for loss recovery are ineffective. Furthermore, TCP is overkill, as not every game packet needs to be transmitted in a reliably and orderly manner. We also show that the degraded network performance did impact users?? willingness to continue a game. Finally, we discuss guidelines in designing transport protocols for online games.


Kuan-Ta Chen, Chun-Ying Huang, Polly Huang, and Chin-Laung Lei, "An Empirical Evaluation of TCP Performance in Online Games," ACM SIGCHI ACE, June 206.


@inproceedings{chen06:tcp, author = {Kuan-Ta Chen and Chun-Ying Huang and Polly Huang and Chin-Laung Lei}, title = {An Empirical Evaluation of {TCP} Performance in Online Games}, booktitle = {Proceedings of ACM SIGCHI ACE 06}, address = {Los Angeles USA}, month = {Jun}, year = {2006} }