(no subject)

This paper describe a content routing design based on name-based
routing as part of an explicit Internet content layer. The authors
claimed that this content routing is a natural extension of current
Internet directory and routing systems, allows efficient content
location, and can be implemented to scale with the Internet.

The goal of content routing is to reduce the time needed to access
content. This is accomplished by directing a client to one of many
possible content servers. The conventional content routing design
does not scale well because it requires the world-wide clients of a
site. DNS-based content routing systems typically use short time-to-
lives on the address records they return to a client. DNS lookup can
be a significant portion of web transaction latency. Conventional
content routing systems may also suffer from other availability
problems, and may have difficult scaling to support multiple content
provider networks and large numbers of content providers.

Clients desire connectivity not to a particular server or IP address
but to some piece of content, specified by name. Based on this
routing problem, authors proposed network-integrated content routing.
It provided support in the core of the Internet to distribute,
maintain, and make use of information about content reachability.
This is performed by routers which are extended to support naming.
These content routers act as both conventional IP routers and name
servers, and participate in both IP routing and name-based routing.
This integration forms the basis of the content layer.

By pushing naming information out into the network, content routers
allow fast location of nearby content replicas in essence, content
routers provide the same service for naming that CDNs do for the
content itself. The authors developed NBRP to distribute names in
this fashion and INRP to perform efficient lookup on this distributed
integrated named-based routing system. The results indicate that
client name lookup is then faster and far less variable.

The main contribution of this paper is to propose a new approach to
tackle the content delivery problem. The key point is to implement
two protocols: INRP and NBRP. There is a problem I meet. When I was
in China, every time, I want to access "www.msn.com", I was directed
to MSN Chinese website. I think because the MSN server in China is
much closer to me compared with the server in US. However, I do want
to access the English MSN website. I do not know how to deal with
this problem. Although the closer server could have low latency, the
content is not what I want. So the point is that the names are the
same, but the real contents are totally different. I think this issue
exits in lots of hot websites, microsoft.com, google.com, and etc.
Received on Tue Nov 28 2006 - 22:11:03 EST