Tracing the Path to YouTube − A Quantification of Path Lengths and Latencies Toward Content Caches
Trinh Viet Doan, Ljubica Pajevic, Vaibhav Bajpai, Jörg Ott
Technical University of Munich
IEEE Communications Magazine, November 2018. Publication →
Presented at MAT WG Meeting, RIPE 77, Amsterdam. Slides →
The dataset is collected from ~100 SamKnows probes:
The raw dataset is available at:
It is stored as a sqlite3 database
youtube-may-2016-2018.db. The schema of the tables can be found under
This repository contains (most of) the required metadata to reproduce the results, see below for further instructions.
To read from the database (see above),
sqlite3 is needed.
The analyses were performed using
jupyter notebooks on
Required Python dependencies are listed in
requirements.txt and can be installed using
pip install -r requirements.txt.
as_types.txt (downloaded from CAIDA's AS Classification →) is used to assign certain types to the ASes seen in the traceroute measurements.
Repeating the results
Move the required datasets and modules to the right locations:
nb-create_tables.ipynb notebook to process and aggregate the raw dataset, which will store the results in a separate database. After that, the other notebooks
nb-*.ipynb can be used to draw the plots presented in the paper.
All plots are saved under
Note: the lookup of metadata was already done, however, it can be repeated by running
Further analyses and results
For a previous version of the dataset (covering measurements from 05/2016 until 03/2017), more analyses and results can be found here →.
Please feel welcome to contact the authors for further details.