---------- Forwarded message ----------
From: Vaibhav Bajpai <bajpaiv@in.tum.de>
Date: Wed, Jul 5, 2017 at 11:50 PM
Subject: measuring youtube over v6
To: Vaibhav Bajpai <bajpaiv@in.tum.de>


Dear v6 hosts,

Do users experience benefit (or suffer) from streaming YouTube videos over IPv6?
--------------------------------------------------------------------------------

To answer this question, we developed a youtube test that measures YouTube
content delivery over IPv4 and IPv6. We deployed this test on ∼100 SamKnows
probes. A paper analysing this ~3 years long dataset ('14 - '17) just came
online. Thought to share it along:

http://vaibhavbajpai.com/documents/papers/proceedings/youtube-ccr-2017.pdf

We will present this at the IETF on Thursday. Please do come to the talk:
https://datatracker.ietf.org/meeting/99/agenda/maprg

Feedback most welcome and thanks for keeping the probe online! :-)

Abstract
--------

We measure YouTube content delivery over IPv6 using ∼100 SamKnows probes
connected to dual-stacked networks representing 66 different origin ASes.
Using a 34-months long (Aug 2014-Jun 2017) dataset, we show that success rates
of streaming a stall-free ver- sion of a video over IPv6 have improved over
time. We show that a Happy Eyeballs (HE) race during initial TCP connection
estab- lishment leads to a strong (more than 97%) preference over IPv6.
However, even though clients prefer streaming videos over IPv6, we observe
worse performance over IPv6 than over IPv4. We witness consistently higher TCP
connection establishment times and startup delays (∼100 ms or more) over IPv6.
We also observe consistently lower achieved throughput both for audio and
video over IPv6. We observe less than 1% stall rates over both address
families. Due to lower stall rates, bitrates that can be reliably streamed
over both address families are comparable. However, in situations, where a
stall does occur, 80% of the samples experience higher stall durations that
are at least 1s longer over IPv6 and have not reduced over time. The worse
performance over IPv6 is due to the disparity in the availability of Google
Global Caches (GGC) over IPv6. The mea- surements performed in this work using
the youtube test and the entire dataset is made available to the measurement
community.

-- Vaibhav

--------------------------
Vaibhav Bajpai
www.vaibhavbajpai.com

Postdoctoral Researcher
TU Munich, Germany
--------------------------