Re: MIT network measurement probes

["David G. Andersen" <dga () lcs mit edu>]

Christopher Wolff just mooed:
> I respect your approach, letting us know about your bandwidth study and what each network operator can expect.  The 
> important part is that we get the opportunity to either opt-out, or find out a way to "opt-in" and help you acquire 
> more information to complete your research.

  All of our hosts will have http and finger servers running on them
that send a brief text file describing what's going on and how to
avoid it.  Where we can, the ping hosts will have descriptive names,
but we can't arrange that everywhere.  Similarly, where possible,
we're creating DNS TXT records that describe the experiments.

  I'd love to hear other suggestions for preemptive "this is what's
going on" indications.  I actually really like the Digital Isle
"put a message in the ICMP messages" approach, since it seems to have
at least gotten the message through in one occasion.  Other ideas
welcome;  feel free to send to me and I'll summarize to the list.

  -Dave
 
--
work: dga () lcs mit edu                          me:  dga () pobox com
      MIT Laboratory for Computer Science           http://www.angio.net/