Searching for mobile mice and elephants in GPRS networks

ABSTRACT

In this paper, we provide statistics on large-scale traffic measurements that have been made in a live cellular GPRS network. We show that the current GPRS traffic is dominated by HTTP- and WAP-based applications, and further show in what direction (uplink and/or downlink) the ensuing traffic is transmitted as well as statistics on the length of the flows on a per application basis. We find that the results differ compared to those found in similar measurement studies that have been carried out in the fixed Internet. In particular, our results suggest that flows are shorter in cellular networks, and that the so-called mice and elephant effect, whereby a small part of the flows make up a majority of the bytes transferred, is not prevalent in GPRS networks. Instead, extremely short flows account for the majority of the total flows and bytes transferred. We also discuss the impact of this finding on future research on TCP loss recovery.

REFERENCES

• 1: 3GPP TS 03.60, "General Packet Radio Service (GPRS); Service description; Stage 2 (Release 1998)
• 2: Apache HTTP Server, (http://httpd.apache.org/), description (http://httpd.apache.org/docs/keepalive.html)
• 3: M. Allman, H. Balakrishnan, S. Floyd, "Enhancing TCP's Loss Recovery Using Limited Transmit", RFC 3042, January 2001
• 4: M. Allman, V. Paxon, W. Stevens, "TCP Congestion Control", RFC 2581, April 1999
• 5: U. Ayesta, K. Avrachenkov, "On reducing the number of TimeOuts for short-lived TCP connections" IETF Internet Draft October 2002 (Work in Progress)
• 6: E. Blanton, M. Allman, K. Fall, L. Wang, "A Conservative Selective Acknowledgement (SACK)-based Loss Recovery Algorithm for TCP", RFC 3517, April 2003
• 7: K. Claffy, H-W. Braun, G. Polyzos "A parametrizable methodology for Internet Traffic flow Profiling" IEEE JSAC, Vol 13, no 8, 1995
• 8: H. Ekström, R. Ludwig, "The Peak-Hopper: A New End-2-End Retransmission Timer for Reliable Unicast Transport", In proceedings of IEEE Infocom 2004
• 9: R. Fielding, J. Mogul, H. Frystyk, et al., "Hypertext Transfer -- Protocol HTTP/1.1", RFC 2616, June 1999.
• 10: C. Fraleigh, S. Moon, C. Diot, B. Lyles, F. Tobagi, "Packet-Level Traffic Measurements from a Tier-1 IP Backbone", Sprint ATL Technical Report TR01-ATL-110101, November 2001
• 11: J. R. Iyengar, A. L. Caro, P. D. Amer, "Dealing with Short TCP Flows: A survey of Mice in Elephant Shoes", under submission, 2003
• 12: K. C. Lan, J. Heidemann, "On the correlation of Internet flow characteristics" under submission, 2003
• 13: M. Mathis, J. Mahdavi, S. Floyd, A. Romanov, "TCP Selective ACKOptions", RFC 2018, October 1996
• 14: H. F. Nielsen, J. Gettys, A. Baird-Smith, et al. June 1997 "Network Performance Effects of HTTP 1.1, CSS1 and PNG" http://www.w3.org/TR/NOTE-pipelining
• 15: V. Paxon, M. Allman, "Computing TCP's Retransmission Timer", RFC 2988, November 2000
• 16: J. C. Mogul, "The Case for Persistent-Connection HTTP" DIGITIAL Western Research Laboratory, Research Report 95/4
• 17: K. Thompson, G. J. Miller, R. Wilder, "Wide-Area Internet Traffic Patterns and Characteristics (Extended Version)" IEEE Network, 11(6), November 1997
• 18: WAP-224-WTP-"Wireless Transaction Protocol" URL: http://www.wapforum.org/
• 19: WAP-225-TCP- "Wireless Profiled TCP" URL: http://www.wapforum.org/
• 20: WAP-229-HTTP-" Wireless Profiled HTTP" URL:http://www.wapforum.org/
• 21: WAP-230-WSP "Wireless Session Protocol Specification" URL:http://www.wapforum.org/
• 22: WAP 2.0 "Technical White Paper" URL:http://www.wapforum.org/