Abstract: TCP congestion-control adopts a fairly slow-bandwidth search process that prevents it from efficiently utilizing end-to-end spare bandwidth in high speed and dynamic environments. Unfortunately, while several alternate congestion-control protocols have been proposed to speed up the search process, most of these struggle to remain non-intrusive to cross-traffic while achieving high speed---consequently, even these 'high-speed' protocols may still take hundreds to thousands of RTTs in searching for available bandwidth in 1-10Gbps networks. With typical link error rates, such protocols can utilize no more than 60% of the spare bandwidth on 10G links.

We argue that the legacy design framework of window-based transmission and control, that fundamentally operates at an RTT timescale, is responsible for this poor scalability behavior. We design a new rate-based framework for congestion-control that allows TCP connections to boldly search for, and adapt to, the available bandwidth within a handful of RTTs. Our key insight is to rethink the timescale at which congestion-control probes for available bandwidth---we show that by shrinking this timescale, it is possible to design a protocol that achieves a high bandwidth-search speed without significantly overloading the network. Our resultant approach relies on carefully orchestrated inter-packet gaps at the sender---that help quickly probe for several different rates using only a few packets---and estimates the available bandwidth based on gap increases at the receiver.

We use this framework to design a new protocol, referred to as RAPID, using mechanisms that promote efficiency, queue-friendliness, and fairness. Our experimental simulations with 1-10Gbps networks indicate that RAPID: (i) converges to an updated value of bandwidth within 1-4 RTTs; (ii) is fairly efficient in utilizing rapidly-varying spare bandwidth; (iii) helps maintain fairly small queues; (iv) has negligible impact on co-existing conventional TCP traffic aggregates; and (v) exhibits excellent fairness among co-existing RAPID transfers. The rate-based design allows RAPID to be truly RTT-fair.

Short Bio: Jasleen Kaur is an Assistant Professor in the Department of Computer Science at the University of North Carolina at Chapel Hill. Her research interests lie in the design and evaluation of networks and operating systems. Her current research efforts are focused on Internet measurements and modeling geared towards understanding the performance of transport protocols. Jasleen is a recipient of the NSF CAREER Award, 2004, and the UNC Junior Faculty Development Award, 2004.

Jasleen received her B.Tech. in Computer Science and Engineering from the Indian Institute of Technology, Kanpur, in 1997, where she was also awarded the Motorola Student of the Year Gold Medal. She earned an M.S. and Ph.D. in Computer Sciences from the University of Texas at Austin in 1999 and 2002, respectively. She is a recipient of the J.C.Browne Graduate Fellowship and the M.C.D. Fellowship from the University of Texas at Austin.