Abstract
In the light of the mice-elephant phenomenon of the Internet traffic, TCP congestion control algorithm shows unfairness against flows of small sizes (small flows). In this context, we find it motivating to study the influence of TCP's initial window (IW) size on the response times of small flows. In our previous works, we proposed a function that determines IW-size for each flow based on its size; through game-theoretic analysis as well as experiments on real testbed, we observed that the size-based IW function (in comparison to a single constant IW size) shows considerable improvement in the performance of small flows, while at the same time not affecting the performance of large flows. In this paper, we share the experience of using some important open source tools for developing, experimenting and evaluating the proposed IW function. We implement the size-based IW function in the Linux kernel, version 3.7.4; we use ipfw/Dummynet for emulating links, open source tool called parallel for executing the application in parallel for generating TCP traffic, wireshark (along with lua script) for extracting metrics for performance analysis. Finally we evaluate the performance of flows using the IW function.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have