<div>Hi Wesley,</div>
<div> </div>
<div>Just saw you post. And I thought you might be interested in a project we are working on with our collabrators. It is an ns2 TCP simulation tool suite. This suite includes a number of typical network topologies, with settable link capacities and traffic matrix. After a simulatioin completes, it automatically generates a set of performance metrics (part of Dr. Sally Floyd's TMRG draft) and graphs, and, with minimal manual effort, can put all the statistics into an HTML page or a paper. We have used this tool suite to evaluate ten protocols with over 10,000 simulations.
</div>
<div> </div>
<div>We will publish an IETF draft to describe our work and the code shortly.</div>
<div> </div>
<div>Best,</div>
<div>Yong Xia</div>
<div>NEC Labs China</div>
<div> </div>
<div>---------- Forwarded message ----------<br>From: Wesley Eddy <<a href="mailto:weddy@grc.nasa.gov">weddy@grc.nasa.gov</a>><br>To: Douglas Leith <<a href="mailto:doug.leith@nuim.ie">doug.leith@nuim.ie</a>>
<br>Date: Tue, 6 Mar 2007 09:42:53 -0500<br>Subject: Re: [Iccrg] benchmarking new tcp congestion control algorithms<br>On Sun, Feb 11, 2007 at 12:28:36PM +0000, Douglas Leith wrote:<br>><br>> Just posted this to the end2end list, but in view of the discussions
<br>> at pfldnet last week and the agenda for the iccrg meeting tomorrow,<br>> it might be topical for iccrg.<br>><br>> I've put together a set of short ns scripts to carry out the tcp<br>> benchmark tests described in
<br>><br>> Experimental evaluation of high-speed congestion control protocols,<br>> Li, Y.T, Leith,D., Shorten,R. Transactions on Networking, 2007 (see<br>> <a href="http://www.hamilton.ie/net/eval/ToNfinal.pdf">
http://www.hamilton.ie/net/eval/ToNfinal.pdf</a>).<br>><br>> The ns scripts are at <a href="http://www.hamilton.ie/net/eval/tcptesting.zip">http://www.hamilton.ie/net/eval/tcptesting.zip</a>.<br>><br>> Its now very easy to rerun these tests against proposed new
<br>> congestion control algorithms. Baseline tests for standard tcp, high-<br>> speed tcp, scalable tcp, bic tcp, fast tcp and htcp are reported in<br>> <a href="http://www.hamilton.ie/net/eval/ToNfinal.pdf">http://www.hamilton.ie/net/eval/ToNfinal.pdf
</a> and these experimental<br>> measurements can be directly compared against the simulation results<br>> generated by the script.<br>><br>> Let me know if you have any comments.<br>><br><br><br>I think these kinds of contributions are very helpful for the community.
<br>I wonder if based on this, it would be possible to propose a "minimal"<br>set of test scenarios and objectives that we could use as a sort of<br>first stage of screening for new congestion control schemes. If we
<br>could come up with some rough consensus on what battery of test results<br>demonstrates that a given scheme is safe, then we could do to things:<br><br>1) leverage the set of tests as a fair and level way to achieve<br>
consensus that particular congestion control schemes that are<br> proposed in the ICCRG are safe to be published as Experimental.<br><br>2) use the test output to refine proposed congestion control schemes,<br> tweak parameters, and understand the differences between schemes
<br><br>All around I think a standard battery of tests and some goals for the<br>tests based on the tmrg-metrics work would be fantastically useful.<br>Does anyone else agree or have cycles to work on this kind of<br>infrastructure for the group?
<br><br>--<br>Wesley M. Eddy<br>Verizon Federal Network Systems<br><br> </div>