[CAnet - news] How to lease the Internet in your spare time - must read

"Bill St.Arnaud" <[email protected]>
Newsgroups gmane.culture.publications.news
Message-ID <01e401c6dd8d$00e67bb0$1400000a@amarillo>
For more information on this item please visit the CANARIE CA*net 4 Optical
Internet program web site at http://www.canarie.ca/canet4/library/list.html
-------------------------------------------



[Excellent paper on the issues facing the current Internet and possible
solution through some of the concepts developed for GENI. The principle of
"concurrent architectures are better than one"  (CABO)is almost identical to
the UCLP technology developed by CANARIE and its partners and deployed
across CA*net 4 where ISPs and users can deploy many virtual concurrent
networks on a common infrastructure. The big difference between UCLP and
CABO is that UCLP uses web services and workflow to allow users, rather than
the infrastructure provider, to build their own concurrent network
architecture with virtual links, routers and switches.  Some excerpts from
the paper.  Thanks to Biswajit Nandy for this pointer.--BSA]  

For the full paper please see..

http://www-static.cc.gatech.edu/~feamster/papers/cabo-tr.pdf#search=%22How%2
0to%20lease%20the%20Internet%20in%20Your%20spare%20time%22

For information on UCLP please see:

http://grid2.canarie.ca/wiki/index.php/UCLPv2
www.uclp.ca
www.uclpv2.ca

ABSTRACT
Today's Internet Service Providers (ISPs) serve two roles:
managing their network infrastructure and providing (arguably
limited) services to end users. We argue that coupling
these roles impedes the deployment of new protocols
and architectures. Instead, the future Internet should support
two separate entities: infrastructure providers (who manage
the physical infrastructure) and service providers (who deploy
network protocols and offer end-to-end services). We
present a high-level design for Cabo, an architecture that enables
this separation, and we describe challenges associated
with realizing this architecture.


1. Introduction
The Internet is relatively resistant to fundamental change.
The last fifteen years have offered countless "false starts" in
the deployment of new services. For example, differentiated
services, IP multicast, and secure routing protocols have not
seen wide-scale deployment, despite offering tangible value
and making significant headway through the protocol standardization
process. A major impediment to deploying these
services is the need for coordination: an Internet service
provider (ISP) that deploys the service garners little benefit
until other domains follow suit [18]. For example, an ISP
that deploys a secure routing protocol like S-BGP [13] incurs
substantial cost but still is not protected from bogus route announcements
unless other ISPs also deploy S-BGP.
ISPs are under immense pressure to offer "value added"
services, in response to both customer demands and the increasing
commoditization of Internet connectivity. Building
a network that has global reach requires either "building it
yourself" or depending on other ISPs for connectivity. ISPs
naturally adopt the latter approach to contain cost. Unfortunately,
because a single ISP rarely has purview over an entire
end-to-end path, new services either have been deployed
only in small islands or have languished entirely. Some ISPs,
hard-pressed to offer profitable services to end users, are
driven to extortionary measures such as degrading service
for some, while providing "better service" (though not better
end-to-end service) for others, as evidenced by the ongoing
"net neutrality" debate [7, 24].

....

We argue that decoupling infrastructure providers (who
deploy and maintain network equipment) from service
providers (who deploy network protocols and offer endto-
end services)1 is the key to breaking this stalemate.
We propose Cabo ("Concurrent Architectures are Better
than One"), which exploits virtualization to allow a service
provider to simultaneously run multiple end-to-end services
over equipment owned by different infrastructure providers.
Cabo extends network virtualization beyond its current use
for supporting shared experimental facilities, such as PlanetLab
[5] and GENI [10]. Rather than simply serving as
an evaluation platform for selecting a single "winning" architecture,
support for virtual networks itself should be the
architecture. Cabo's design adopts the pluralist philosophy
[4], which advocates a flexible and extensible system
that supports multiple simultaneous network architectures.
....



-------------------------------------
To SUBSCRIBE:
send a blank e-mail message to
[email protected]

To UNSUBSCRIBE:
send a blank email message to
[email protected]
-------------------------------------

These news items and comments are mine alone and do not necessarily reflect
those  of the CANARIE board or management.

-----------
[email protected]
www.canarie.ca/~bstarn
skype: pocketpro
SkypeIn: +1 614 441-9603


_______________________________________________
news mailing list
[email protected]
http://lists.canarie.ca/mailman/listinfo/news
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.