Giter Site home page Giter Site logo

kemanth / implementation-of-madpie-in-linux-kernel Goto Github PK

View Code? Open in Web Editor NEW
0.0 3.0 2.0 172.35 MB

Implementation of MADPIE AQM in Linux Kernel

License: Other

Makefile 0.24% C 96.20% Assembly 1.50% C++ 1.77% Objective-C 0.12% Shell 0.03% Prolog 0.03% Awk 0.01% Perl 0.08% Python 0.01% GDB 0.01% SourcePawn 0.01% Perl 6 0.01% Yacc 0.01% Lex 0.01% UnrealScript 0.01%

implementation-of-madpie-in-linux-kernel's Introduction

Implementation of MADPIE algorithm in Linux kernel

Course Code: CS822

Assignment: #FP4

Overview

Maximum and Average queuing Delay with Proportional Integral controller Enhanced (MADPIE) [1] is an extension of PIE [2], that adds deterministic packet drops at controlled intervals. This repository provides an implementation of MADPIE in the Linux kernel.

Steps to build the modified kernel with MADPIE algorithm

  1. Download or clone this repository on your local machine

  2. Configure the kernel

    make menuconfig

  3. Compile the kernel

    make

  4. Build and install the modules

    make modules

    make modules_install

  5. Install the kernel

    make install

Steps to test the functionality of MADPIE AQM by using Flexible Network Tester (Flent) [3]

  1. Setup a physical topology of three nodes:

    Client <---> Router <---> Server

  2. Create a separate passwordless SSH connection between client and router machines, so that Flent can collect queue statistics from the router machine

  3. Install Netserver in server machine

  4. Install Flent from github or ppa repository in client machine

  5. Install the modified kernel with MADPIE algorithm in router machine

  6. Run Flent for plotting different graphs

Syntax of the command to run Flent

./run-flent rrul -p [PLOT_NAME] -l 160 -H [SERVER_IP] --test-parameter bandwidth=800M --test-parameter qdisc_stats_hosts=[ROUTER_SSH_IP] --test-parameter qdisc_stats_interfaces=[ROUTER_AQM_INTERFACE] --test-parameter upload_streams=num_cpus --test-parameter download_streams=num_cpus -t MADPIE -o ~/Desktop/MADPIE/test.png

PLOT_NAME - The type of graph needed

SERVER_IP - IP Address of the server

ROUTER_SSH_IP - IP Address using which ssh connection is setup with router

ROUTER_AQM_INTERFACE - Interface name of the router where AQM is installed

Example command to run Flent

./run-flent rrul -p all_scaled -l 160 -H 172.16.10.2 --test-parameter bandwidth=800M --test-parameter qdisc_stats_hosts=192.168.20.2 --test-parameter qdisc_stats_interfaces=eth1 --test-parameter upload_streams=num_cpus --test-parameter download_streams=num_cpus -t MADPIE -o ~/Desktop/MADPIE/test.png

References

[1] Kuhn, N., & Ros, D. (2016). Improving PIE's performance over high-delay paths. arXiv preprint arXiv:1602.00569.

[2] Pan, R., Natarajan, P., Piglione, C., Prabhu, M. S., Subramanian, V., Baker, F., & VerSteeg, B. (2013, July). PIE: A lightweight control scheme to address the bufferbloat problem. In High Performance Switching and Routing (HPSR), 2013 IEEE 14th International Conference on (pp. 148-155). IEEE.

[3] Flent: The FLExible Network Tester (https://flent.org/)

implementation-of-madpie-in-linux-kernel's People

Contributors

harishnitk avatar kemanth avatar mohittahiliani avatar

Watchers

 avatar  avatar  avatar

implementation-of-madpie-in-linux-kernel's Issues

Make final changes to the Wiki

Update the wiki by summarizing the project.

See Sourabh's, Viyom's or Vivek's project repos to see how to prepare a short summary.

Close this issue once done.

Prepare a new patch

Incorporate the latest suggestions in your code, and prepare a fresh patch.

Give the extension of the patch file as .patch

Send the new patch to me, Sourabh and Sachin.

Update the README

In the readme, after the 'Overview' section - please provide steps for the reader so that they can download your repo, build the linux kernel and test the working of MADPIE.

You can mention about the topology that you have used in flent, or may be point the reader to a specific test in flent which you've used.

Give one line description

Currently, at the top of the repo it says:

No description, website, or topics provided.

Change this and add one line description of the project.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.