Pantek Library
Hosting Provided By
CybrHost
High Speed Hosting

[e2e] A new version of NS-2 TCP-Linux

From: Xiaoliang (David) Wei <weixl(at)caltech.edu>
Date: Mon Oct 01 2007 - 03:01:53 EDT


Dear Colleagues,

    I'd like to announce a new version of NS-2 TCP-Linux, which runs congestion control module source codes from Linux in NS-2 simulation. This new version has the following features:

  1. incorporates 14 congestion control algorithms in Linux 2.6.22-6 into NS-2.31 (also compatible with NS-2.29 and NS-2.30);
  2. allows to set new values for parameters of different congestion control algorithms so that we can study the effects/sensitivities of parameter setting in these algorithms.

    The simulation speed and memory usage are still very similar to other standard NS-2 TCPs (such as Sack1) and the usage is almost the same as the current NS TCPs (except adding one command to select congestion control module and optionally two commands to set new parameter values).

    The new patch can be downloaded from http://www.cs.caltech.edu/~weixl/technical/ns2linux/index.html and the page has more details on the usage.

    There is an updated tutorial which provides simple usage examples: http://www.cs.caltech.edu/~weixl/technical/ns2linux/tutorial/index.html

    If you find any problem, please let me know.:)

A little bit more details (See the links above for more details):

  1. In the patch, I added a new TCP class which is called LinuxTCPAgent. The class loosely follows the ack processing path in Linux TCP with many simplifications. It calls congestion control modules to change the cwnd and ssthreshold, as Linux does. You can always add your own congestion control algorithms with minor modifications, as long as you get the source codes of their Linux congestion control modules.
  2. I also added a new Scoreboard design which can process SACK in a similar way as Linux does, while maintaining the similar simulation speed as scoreboard-rq.
  3. Some Limitations: D-SACK, F-RTO and ECN process is yet to be implemented. Also, since the TCPSink in NS2 has some difference from Linux receiver process, the cwnd trajectory from simulation results are not exactly the same as Linux experiments.

-David

Do you need help?X

--

Xiaoliang (David) Wei EAS @ Caltech http://www.DavidWei.org


Received on Mon Oct 1 03:41:24 2007

This archive was generated by hypermail 2.1.8 : Mon Oct 29 2007 - 14:15:46 EDT


Contact Us  Legal Notices  Order Services Online 
Pantek Home  Privacy Policy  IT news  Site Map  Pantek Library