The TCP Minimum RTO Revisited

We re-examine the two reasons for the conservative 1-second Minimum TCP-RTO to protect against spurious timeouts: i) the OS clock granularity and ii) the Delayed ACKs. We find that reason (i) is canceled in modern OSs; we carefully design a mechanism to deal with reason (ii). Simulation results show that in next generation's high-speed, wireless-access networks, TCP-RTO should not be limited by a fixed, conservative lower bound.

[1]  Van Jacobson,et al.  TCP Extensions for High Performance , 1992, RFC.

[2]  Sally Floyd,et al.  TCP Selective Acknowledgement Options , 1996 .

[3]  Robert T. Braden,et al.  Requirements for Internet Hosts - Communication Layers , 1989, RFC.

[4]  Vern Paxson,et al.  Computing TCP's Retransmission Timer , 2000, RFC.

[5]  Sally Floyd,et al.  Measuring interactions between transport protocols and middleboxes , 2004, IMC '04.

[6]  Sally Floyd,et al.  Measuring the evolution of transport protocols in the internet , 2005, CCRV.

[7]  QUTdN QeO,et al.  Random early detection gateways for congestion avoidance , 1993, TNET.

[8]  Vern Paxson,et al.  On estimating end-to-end network path properties , 2001, SIGCOMM LA '01.

[9]  Reiner Ludwig,et al.  Responding to spurious timeouts in TCP , 2003, IEEE INFOCOM 2003. Twenty-second Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE Cat. No.03CH37428).

[10]  Vern Paxson,et al.  TCP Congestion Control , 1999, RFC.

[11]  Kimmo E. E. Raatikainen,et al.  F-RTO: an enhanced recovery algorithm for TCP retransmission timeouts , 2003, CCRV.

[12]  Pasi Sarolahti,et al.  Congestion Control in Linux TCP , 2002, USENIX Annual Technical Conference, FREENIX Track.

[13]  Ioannis Psaras,et al.  Why TCP timers (still) don't work well , 2007, Comput. Networks.