RE: [IMRG] directing the discussion

From: Jennifer Rexford <jrex(at)CS.Princeton.EDU>
Date: Wed Mar 16 2005 - 17:52:22 EST

> A key question (in my mind) is: Now that we know better how to do it,
> what is Internet Measurement good for? Or more precisely, who needs
> that information and under what circumstances?

Good question. I think we're now at the point where publishing analysis of Internet measurement data is no longer a novelty. So, the bar should naturally get higher for what consistitutes "research" in this area -- work that lends new/deep insight into the behavior of a system or protocol, or work that adds new methods and techniques to our bag of tricks. (Also, I think students are in a position now where doing an entire PhD thesis on collecting and characterizing measurement data might not be "enough". They might reasonably need to use the insights from the data analysis to redesign a system, create new algorithms, etc. That is, measurement and data analysis might be a phase in the work, rather than the entire body of the work.)

Also, I would argue that the body of existing work has grown so large (and so quickly) that it is getting hard for new people to jump in to the area, and existing folks to keep up with what's going on. (Henk alluded to this problem as well, in commenting on how many different venues have a significant emphasis on Internet measurement. Actually, even putting together a simple Web site that linked to the main venues would be a useful contribution at this point!)

In terms of the important question of "who needs the information," I think we have at least two camps -- those using data to characterize the beast (e.g., research folks trying to do experimental science on the Internet, including work on understanding the performance and limitations of our existing protocols and/or evaluate new designs) and those using data to run the network (e.g., operators trying to detect anomalies, do traffic engineering, thwart attacks, etc.), though increasingly the lines are blurry as more research folks jump in to creating and evaluating techniques for using measurement data to help operators.

• Jen

-----Original Message-----
From: imrg-bounces@ietf.org [mailto:imrg-bounces@ietf.org] On Behalf Of Loki Jorgenson
Sent: Thursday, March 10, 2005 6:13 PM
To: imrg@ietf.org
Subject: [IMRG] directing the discussion

Mark - my reflections would parallel Jennifer's - measurement has matured to a certain point and I feel that it is time for it to make itself relevant to other things - integrate with the larger world and/or be part of other systems that need measurement. In other words, can we get down to applied research?

Jennifer listed some options to consider.

A key question (in my mind) is: Now that we know better how to do it, what is Internet Measurement good for? Or more precisely, who needs that information and under what circumstances?

My experience as an industry researcher has been that the answer to this question is non-trivial and not what you'd expect. For example, in general I would say that core network engineers "don't care" - however, applications people (who have little direct access to the network) care a great deal but in specific ways and under specific circumstances.

Jennifer Rexford wrote:

---

Message: 1
Date: Wed, 9 Mar 2005 21:38:00 -0500
From: "Jennifer Rexford" <jrex@CS.Princeton.EDU> Subject: RE: [IMRG] imrg futures
To: <mallman@icir.org>
Cc: imrg@irtf.org
Message-ID: <200503100238.j2A2cWn3003271@bluebox.CS.Princeton.EDU> Content-Type: text/plain; charset="us-ascii"

Mark,

Hi, thanks for getting the ball rolling. Here are a few thoughts to give
the ball an additional kick. I'm not sure which of these (if any) make sense specifically in a context like IMRG, but these are some measurement-related things I've been thinking or wondering about...

• Education/curriculum:
• Network support for measurement:
• Measurement in support of network operations:
  • Jen

Loki Jorgenson
Chief Scientist
Apparent Networks
The Hudson House
Suite 400 - 321 Water Street
Vancouver, BC, Canada, V6B 1B8

e ljorgenson@ApparentNetworks.com
t 604 433 2333 ext 105
f 604 433 2311
m 604 340-2480
w www.ApparentNetworks.com

---

IMRG mailing list
IMRG@ietf.org
https://www1.ietf.org/mailman/listinfo/imrg

---

IMRG mailing list
IMRG@ietf.org
https://www1.ietf.org/mailman/listinfo/imrg Received on Wed Mar 16 17:53:26 2005