[e2e] Internet delay and jitter measurement

David G. Andersen dga at lcs.mit.edu
Wed Jul 2 19:24:58 PDT 2003

On Fri, Jun 27, 2003 at 08:34:28PM -0700, Ping Pan quacked:
> Hi,
> A few years ago, Vern Paxson had measured: the end-to-end packet delay 
> varies from 100 to 1,000 msec, and extended out quite frequently to much 
> longer times.
> Is there any new measurement on this topic? I guess the results have a 
> lot to do with where the measurements are done. Over the years, a number 
> of providers have done the study inside their backbone... No kidding, 
> there was no delay considering all those under-utilized links. Just 
> wondering if people have some real "end-to-end" data.

  Depends what you're looking for.  I don't have too much fine-grained
jitter data, but I have end-to-end ping data taken every ~40 seconds
between 30 hosts over the last two years.  More than happy to share
if you'd like it, or want a subset of it.  It's kind of voluminous,
but that's what the internet 2 is for. ;-)

(offer extends to everyone, of course).


work: dga at lcs.mit.edu                          me:  dga at pobox.com
      MIT Laboratory for Computer Science           http://www.angio.net/
      I do not accept unsolicited commercial email.  Do not spam me.

More information about the end2end-interest mailing list