GithubHelp home page GithubHelp logo

cn-tu / cocoa-qdisc Goto Github PK

View Code? Open in Web Editor NEW
8.0 4.0 5.0 28.56 MB

Cocoa is a qdisc which maximizes throughput for each flow while keeping the buffer minimal. Contact: Maximilian Bachl.

Home Page: https://dl.acm.org/doi/10.1145/3375235.3375236

License: GNU General Public License v2.0

Makefile 0.51% C 87.86% Python 1.83% TeX 7.11% Go 2.69%
congestion-control aqm active-queue-management fair-queuing kernel-module qdisc

cocoa-qdisc's Introduction

cocoa-qdisc

Contact: Maximilian Bachl

Cocoa is a qdisc which maximizes throughput for each flow while keeping the buffer minimal. For a more detailed description check out the paper presented at the Buffer Sizing Workshop 2019 (arxiv).

Building

To compile the kernel module run

make

to install it and load it into the kernel run

sudo make install

Next, to make tc aware of the module, change into the iproute2 folder cd iproute2 and run

make
sudo make install

Deploying

Finally, you can use the qdisc on an interface:

sudo tc qdisc replace dev <interface> root cocoa

tc also allows you to specify options like this:

sudo tc qdisc replace dev <interface> root cocoa initial_quantum 3028 quantum 3028

Experimenting

To run experiments, make sure you have py-virtnet (GitHub repository) installed and then run

sudo bash -c 'echo > /sys/kernel/debug/tracing/trace' && sudo bash -c 'echo 1 > /sys/kernel/debug/tracing/tracing_on' && sudo python3 test.py --path_to_tc_module <path to the repository>/cocoa-qdisc/iproute2/tc --rate 100 --delay_to_add 100 --time 240 --qdisc cocoa --change 1 --cc cubic

After running experiments with cocoa, you can look at detailed output in the kernel tracing file at /sys/kernel/debug/tracing/trace.

Analyzing

To create plots of a run and show further statistics, first compile wintracker:

go build -o wintracker wintracker.go

Then, if you have a file called sender_fq_codel_cubic_1_20_120_1.0_bw_1571822805075.pcap in the pcaps directory you can run the plotting script:

./plot_rtt_and_bandwidth.py sender_fq_codel_cubic_1_20_120_1.0_bw_1571822805075.pcap

All tests were performed on kernel 4.19.0-6-amd64 on Debian Buster. We use Python 3.7.2. Our go version is go1.10.2 linux/amd64.

cocoa-qdisc's People

Contributors

muxamilian avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

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.