Jupyter notebooks used for analysis
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
Cdf.py
Makefile
Pmf.py
README.md
asinfo.py
clusterbycolumn.py
filterbyip.py
matplotlibrc
plot-google-v6-adoption.ipynb
plot-stall-duration-cdf.ipynb
plot-stall-duration-timeseries.ipynb
plot-stall-rates-cdf.ipynb
plot-success-rate-cdf.ipynb
plot-success-rate-timeseries.ipynb
plot-tcp-connect-time-startup-delay-difference.ipynb
plot-tcp-connect-time-startup-delay-prebuffering-duration-difference-timeseries.ipynb
plot-throughput-difference-audio-video-timeseries.ipynb
plot-throughput-difference-audio-video.ipynb
plot-v6-preference-cdf.ipynb
requirements.txt
style-notebook.css
style-table.css

README.md

Measuring YouTube Content Delivery over IPv6 →
ACM SIGCOMM Computer Communication Review →
October 2017


Test

The youtube test used to collect the dataset is available here →

Vantage Points

The dataset is collected from ~100 SamKnows probes:

Dataset

The raw dataset and mirrors are available at:

It includes the SQL schema youtube.sql and the dataset in sqlite3 format youtube.db and the metadata associated with each vantage point.

Installation

make will install the python dependencies required to run the jupyter notebooks. make run will run jupyter.

Repeating the results

plot-* notebooks can be used to repeat the analysis on the existing dataset. Each such notebook produces a single plot in the paper.

Contact

Please feel welcome to contact the authors for further details.