Skip to Content.
Sympa Menu

ntacpeering - Re: heads up on Microsoft future peering announcement

Subject: NTAC Peering Working Group

List archive

Re: heads up on Microsoft future peering announcement


Chronological Thread 
  • From: "Hutchins, Ronald R" <>
  • To: David Farmer <>
  • Cc: Chris Robb <>, NTAC <>, NTAC Peering and Routing WG <>, "David Crowe, Jr." <>
  • Subject: Re: heads up on Microsoft future peering announcement
  • Date: Fri, 24 May 2013 11:15:33 -0400 (EDT)
  • Authentication-results: sfpop-ironport07.merit.edu; dkim=neutral (message not signed) header.i=none

But if we fill our pipes with Amazon and Microsoft transactions that
could/should
go over the ISP or TR/CPS links we kill our headroom for research traffic
like the
LHC... ???

----- Original Message -----
From: "David Farmer"
<>
To: "David Crowe, Jr."
<>
Cc: "Chris Robb"
<>,
"NTAC"
<>,
"NTAC Peering and Routing WG"
<>,
"David Farmer"
<>
Sent: Friday, May 24, 2013 10:18:13 AM
Subject: Re: heads up on Microsoft future peering announcement

While I think better tools to allow more local influence over the
routing is a good thing and necessary. However, I also think it is
critical for the Net+ service providers to be included in the R&E side
of the network. There are a number of initiatives to move research to
into these cloud services. Research conducted using cloud based
infrastructure is still research and deserves access to the R&E network
just as much research conducted using campus or lab based infrastructure.

The researchers want access to the cost efficiencies in computing that
these monster-scale cloud providers are creating. If that makes our
lives more difficult, so what. If we don't connect the R&E network to
these monster-scale cloud providers it is possible there will no longer
be a need for the R&E network in a few years.

Just like the Internet started to escaped the lab 20 years ago, gird
computing has escaped the lab too, it just taken on a different name
when it did, cloud computing.

This is NOT about some conspiracy to replacing TR/CPS or pollute the R&E
network with commodity traffic, it is about making sure research has
access to the R&E network regardless where in the cloud/Internet it is
located. Does this change make our lives a little more difficult, sure
it does. But, we have to find a way to evolve the R&E network to meet
the changing needs of research, otherwise we should give up on the R&E
network as a concept.

Thanks.

--
================================================
David Farmer Email:

Office of Information Technology
University of Minnesota
2218 University Ave SE Phone: 1-612-626-0815
Minneapolis, MN 55414-3029 Cell: 1-612-812-9952
================================================



Archive powered by MHonArc 2.6.16.

Top of Page