Benchmarking

From WiL

Benchmarking of TCP protocols is the quantitative comparison of the performance of a new TCP proposal with the performance of other varieties on a standardised set of tests.

WAN-in-Lab is currently being configured to enable TCP benchmarking, both within Netlab, Caltech and the broader communications community.

[edit] Web interface

A publicly available Web interface is currently being developed for WAN-in-Lab' benchmarking suite. This interface allows users to upload experimental kernels, instrumented with the Web100 tools, and to run a set of predefined tests. The results of these tests are then processed and placed on the web in both graphical and numerical form. Protocols are tested for RTT fairness, convergence speed both with and without existing large flows, interaction with short flows, and fairness between flows traversing different numbers of hops.

[edit] Your contributions

WAN-in-Lab is open to suggestions from the broader community, in addition to some of our plans listed on the website.
Please add your thoughts/opinions/contributions by contacting us with your name, institution and suggestions. Thank you.

We are especially interested in your suggestions regarding the following pages:

• Benchmarking objectives
• Meta-benchmarking
• Software infrastructure
• Experiments
• Metrics

[edit] See also

• Traffic models
• Traffic traces