"You make it fun; we'll make it run"

Coral

The Coral Content Distribution Network

•• Project home page
•• Brief overview and news
•• Coral Wiki and FAQ
•• Mailing Lists
•• Publications and people

News

    20 Aug 2012:   We're still here! While active development has been stopped for a while, we continue to operate CoralCDN as an open, free service. It's now been running continuously for more than 8 years (since March 2004), and continues to get a few million users per day at last check. Enjoy continuing to use the service!

    11 Jul 2012:   CoralCDN used with special URL shortener during the 2011 Japan earthquake/tsunami. Read more on the ACM's Digital Library.

    30 Mar 2010:   Experiences paper describing five years running CoralCDN posted.

    24 Mar 2006:   CoralCDN integrates client-side measurements network-wide.

    18 Feb 2006:   CoralCDN begins using port 8080 in addition to port 8090.

    15 Nov 2005:   CoralCDN serves nearly 20 million requests per day from 2.75 million unique clients.

    View all announcements...

Overview

The availability of content on the Internet is to a large degree a function of the cost shouldered by the publisher. A well-funded web site can reach huge numbers of people through some combination of load-balanced servers, fast network connections, and commercial content distribution networks (CDNs). Publishers who cannot afford such amenities are limited in the size of audience and type of content they can serve. Moreover, their sites risk sudden overload following publicity, a phenomenon nicknamed the ``Slashdot'' effect, after a popular web site that periodically links to under-provisioned servers, driving unsustainable levels of traffic to them. Thus, even struggling content providers are often forced to expend significant resources on content distribution.

Fortunately, at least with static content, there is an easy way for popular data to reach many more people than publishers can afford to serve themselves---volunteers can mirror the data on their own servers and networks. Indeed, the Internet has a long history of organizations with good network connectivity mirroring data they consider to be of value. More recently, peer-to-peer file sharing has demonstrated the willingness of even individual broadband users to dedicate upstream bandwidth to redistribute content the users themselves enjoy. Additionally, organizations that mirror popular content reduce their downstream bandwidth utilization and improve the latency for local users accessing the mirror.

What CoralCDN offers

CoralCDN is a decentralized, self-organizing, peer-to-peer web-content distribution network. CoralCDN leverages the aggregate bandwidth of volunteers running the software to absorb and dissipate most of the traffic for web sites using the system. In so doing, CoralCDN replicates content in proportion to the content's popularity, regardless of the publisher's resources---in effect democratizing content publication.

To use CoralCDN, a content publisher---or someone posting a link to a high-traffic portal---simply appends .nyud.net to the hostname in a URL. Through DNS redirection, oblivious clients with unmodified web browsers are transparently redirected to nearby Coral web caches. These caches cooperate to transfer data from nearby peers whenever possible, minimizing both the load on the origin web server and the end-to-end latency experienced by browsers.

CoralCDN is built on top of a novel key/value indexing infrastructure called Coral. Two properties make Coral ideal for CDNs. First, Coral allows nodes to locate nearby cached copies of web objects without querying more distant nodes. Second, Coral prevents hot spots in the infrastructure, even under degenerate loads. For instance, if every node repeatedly stores the same key, the rate of requests to the most heavily-loaded machine is still only logarithmic in the total number of nodes.

Coral exploits overlay routing techniques recently popularized by a number of peer-to-peer distributed hash tables (DHTs). However, Coral differs from DHTs in several ways. First, Coral's locality and hot-spot prevention properties are not possible for DHTs. Second, Coral's architecture is based on clusters of well-connected machines. Clusters are exposed in the interface to higher-level software, and in fact form a crucial part of the DNS redirection mechanism. Finally, to achieve its goals, Coral provides weaker consistency than traditional DHTs. For that reason, we call its indexing abstraction a distributed sloppy hash table or DSHT.

CoralCDN makes a number of contributions. It enables people to publish content that they previously could not or would not because of distribution costs. It is the first completely decentralized and self-organizing web-content distribution network. Coral, the indexing infrastructure, provides a new abstraction potentially of use to any application that needs to locate nearby instances of resources on the network. Coral also introduces an epidemic clustering algorithm that exploits distributed network measurements. Furthermore, Coral is the first peer-to-peer key/value index that can scale to many stores of the same key without hot-spot congestion, thanks to a new rate-limiting technique. Finally, CoralCDN contains the first peer-to-peer DNS redirection infrastructure, allowing the system to inter-operate with unmodified web browsers.

Measurements of CoralCDN demonstrate that it allows under-provisioned web sites to achieve dramatically higher capacity, and its clustering provides quantitatively better performance than locality-unaware systems.


For more detailed technical information, please see our publications page.