TCP performance over end-to-end rate control and stochastic available capacity

Motivated by TCP over end-to-end ABR, we study the performance of adaptive window congestion control, when it operates over an explicit feedback rate- control mechanism, in a situation in which the bandwidth available to the e lastic traffic is stochastically time varying. It is assumed that the sende r and receiver of the adaptive window protocol are colocated with the rate- control endpoints. The objective of the study is to understand if the inter action of the rate-control loop and the window-control loop is beneficial f or end-to-end throughput, and how the parameters of the problem (propagatio n delay, bottleneck buffers, and rate of variation of the available bottlen eck bandwidth) affect the performance. The available bottleneck bandwidth is modeled as a two-state Markov chain. We develop an analysis that explicitly models the bottleneck buffers, the d elayed explicit rate feedback, and TCP's adaptive window mechanism. The ana lysis, however, applies only when the variations in the available bandwidth occur over periods larger than the round-trip delay. For fast variations o f the bottleneck bandwidth, we provide results from a simulation on a TCP t estbed that uses Linux TCP code, and a simulation/emulation of the network model inside the Linux kernel. We find that, over end-to-end ABR, the performance of TCP improves signific antly if the network bottleneck bandwidth variations are slow as compared t o the round-trip propagation delay. Further, we find that TCP over ABR is r elatively insensitive to bottleneck buffer size. These results are for a sh ort-term average link capacity feedback at the ABR level (INSTCAP). We use the testbed to study EFFCAP feedback, which is motivated by the notion of t he effective capacity of the bottleneck link. We find that EFFCAP feedback is adaptive to the rate of bandwidth variations at the bottleneck link, and thus yields good performance (as compared to INSTCAP) over a wide range of the rate of bottleneck bandwidth variation. Finally, we study if TCP over ABR, with EFFCAP feedback, provides throughput fairness even if the connect ions have different round-trip propagation delays.