On 2010-7-20, at 21:00, Yuchung Cheng wrote:
This is very interesting study! it provides many useful information for the
TCP research at Google.
thanks! Let's chat at the IETF if there are any tests we can do that would make
the results even more relevant for you guys?
The queuing and processing delays on slide 12 (or figure 9 in the paper) are
mostly <50ms, but the following paper
"Characterizing residential broadband networks" published in IMC 2007
measures much higher queuing length ranging from 100ms to a few secs
(http://portal.acm.org/citation.cfm?id=1298306.1298313 figure 13).
Any idea about the differences?
We haven't looked into the details much. One factor may be that the delay
numbers we measured where taken at the same time we did the bulk throughput
measurements, and they only used a single connection up and/or down. And IIRC
we measured the delay experience by that connection and not the delay
experienced by other connections through the box at the time. It may also be
that our population is home gateways is newer (= better?) than the one measured
by the IMC paper. We'll attempt to look into this more deeply during the next
phase of the study.
On Fri, Jul 9, 2010 at 12:15 AM, Lars Eggert
a quick status update. We now have received over 100 donated home gateways,
plus a DSLAM. The students are on their summer break, after which we'll start
running a significantly expanded set of tests over this much larger
population of devices.
Many of yo have donated boxes and suggested more experiments and better ways
of performing our current tests - thank you!
In case you are attending IETF-78 in Maastricht and would like to donate a
home gateway, simply bring it. (Or contact me now for shipping details; no
cost to you.)
We're especially interested in devices from outside the EU and North America,
or any other model we may not have yet (see
http://fit.nokia.com/lars/tmp/2010-hgw-study-devices.txt). And we're still
lacking a CMTS for testing cable modems...
See you in Maastricht,
On 2010-6-2, at 18:36, Lars Eggert wrote:
FYI, a first report with test results for 34 devices is available at
http://fit.nokia.com/lars/tmp/2010-hgw-study.pdf. Slides that summarize the
results are at http://fit.nokia.com/lars/tmp/2010-hgw-study-slides.pdf.
We have received another 30-odd devices as donations, which we'll add to the
testbed and include in a follow-up study.
If you have an unused, spare home gateway to donate to this effort, please
contact us at
We're also interested in obtaining a DSLAM and a CMTS.
On 2010-4-29, at 12:34, Lars Eggert wrote:
for a measurement study done together with Markku Kojo's team at the
University of Helsinki, we're looking to collect as many different NAT home
routers as possible. If you have an old clunker lying around somewhere,
please contact me off-list. I'll cover shipping via DHL. Feel free to
forward this email as you see fit.
The boxes will find a permanent home at the University of Helsinki. Study
results will be published openly. The intent is that this collection become
a resource for the community to be shared for future studies.
Caveat: The boxes should NAT between Ethernet interfaces - we don't have
DSL or cable access equipment in the lab setup at the moment.
78attendees mailing list
Ietf mailing list