TY - CONF
T1 - Democratizing content publication with Coral
AU - Freedman, Michael J.
AU - Freudenthal, Eric
AU - Mazières, David
N1 - Funding Information:
Acknowledgments. We are grateful to Vijay Karam-cheti for early conversations that helped shape this work. We thank David Andersen, Nick Feamster, Daniel Gif-fin, Robert Grimm, and our shepherd, Marvin Theimer, for their helpful feedback on drafts of this paper. Petar Maymounkov and Max Krohn provided access to Kadem-lia data structure and HTTP parsing code, respectively. We thank the PlanetLab support team for allowing us the use of UDP port 53 (DNS), despite the additional hassle this caused them. Coral is part of project IRIS (http://project-iris.net/), supported by the NSF under Cooperative Agreement No. ANI-0225660. David Mazières is supported by an Alfred P. Sloan Research Fellowship. Michael Freedman is supported by an NDSEG Fellowship.
Publisher Copyright:
© NSDI 2004.
PY - 2004
Y1 - 2004
N2 - CoralCDN is a peer-to-peer content distribution network that allows a user to run a web site that offers high performance and meets huge demand, all for the price of a cheap broadband Internet connection. Volunteer sites that run CoralCDN automatically replicate content as a side effect of users accessing it. Publishing through CoralCDN is as simple as making a small change to the hostname in an object's URL; a peer-to-peer DNS layer transparently redirects browsers to nearby participating cache nodes, which in turn cooperate to minimize load on the origin web server. One of the system's key goals is to avoid creating hot spots that might dissuade volunteers and hurt performance. It achieves this through Coral, a latency-optimized hierarchical indexing infrastructure based on a novel abstraction called a distributed sloppy hash table, or DSHT.
AB - CoralCDN is a peer-to-peer content distribution network that allows a user to run a web site that offers high performance and meets huge demand, all for the price of a cheap broadband Internet connection. Volunteer sites that run CoralCDN automatically replicate content as a side effect of users accessing it. Publishing through CoralCDN is as simple as making a small change to the hostname in an object's URL; a peer-to-peer DNS layer transparently redirects browsers to nearby participating cache nodes, which in turn cooperate to minimize load on the origin web server. One of the system's key goals is to avoid creating hot spots that might dissuade volunteers and hurt performance. It achieves this through Coral, a latency-optimized hierarchical indexing infrastructure based on a novel abstraction called a distributed sloppy hash table, or DSHT.
UR - http://www.scopus.com/inward/record.url?scp=84888564550&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84888564550&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:84888564550
T2 - 1st Symposium on Networked Systems Design and Implementation, NSDI 2004
Y2 - 29 March 2004 through 31 March 2004
ER -