TCP NewReno: Slow-but-Steady or Impatient?

Abstract

In this paper, we compare the throughputs of two different TCP NewReno variants, namely Slow-but-Steady and Impatient. We develop analytic throughput models of these variants as a function of round-trip time, loss event rate, and the burstiness of packet drops within a loss event. Our models build upon prior work on TCP Reno throughput modeling, but extend this work to provide an analytical characterization of the NewReno fast recovery algorithms. We validated our models using the ns-2 simulator. Our models accurately predict the steady-state NewReno throughput for a wide range of loss rates. Based on these models, we analytically determine the preferred operating regions for each TCP variant. Our results show that the Slow-but-Steady variant is comparable to or superior to the Impatient variant in all but the most extreme scenarios for network packet loss.

Optimal configuration for satellite PEPs using a reliable service on top of a routers-assisted approach

“…error bits) other than congestion. The authors in [16] show similar results when TCP New Reno is used and less than 20 packets per congestion window are lost.…”

Queuing Theory and Telecommunications

“…Totally, the FR/FR procedure has 3 RTTs before RTO expires and can recover 3 packets. Hence, if the total number of lost packets in the same window of data is greater than 3, there is an RTO expiration with the Impatient version [50]. Instead, in the Slow-but-Steady case, the FR/FR phase continues slowly recovering 1 packet per RTT without RTO expirations; when the FR/FR phase ends, a congestion avoidance phase starts.…”

TCP Vegas Performance with Streaming Media

“…Stochastic models of congestion window evolution of popular TCP implementations established that the throughput of TCP Reno [6,16,20,21] and its variants such as NewReno [23] is inversely proportional to the product of RTT and square root of packet loss rate. Recently, Samios et al [27] developed a model for TCP Vegas from which throughput can be estimated.…”