Experiences with CoralCDN: a five-year operational view

  • Authors:
  • Michael J. Freedman

  • Affiliations:
  • Princeton University

  • Venue:
  • NSDI'10 Proceedings of the 7th USENIX conference on Networked systems design and implementation
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

CoralCDN is a self-organizing web content distribution network (CDN). Publishing through CoralCDN is as simple as making a small change to a URL's hostname; a decentralized DNS layer transparently directs browsers to nearby participating cache nodes, which in turn cooperate to minimize load on the origin webserver. CoralCDN has been publicly available on PlanetLab since March 2004, accounting for the majority of its bandwidth and serving requests for several million users (client IPs) per day. This paper describes CoralCDN's usage scenarios and a number of experiences drawn from its multi-year deployment. These lessons range from the specific to the general, touching on the Web (APIs, naming, and security), CDNs (robustness and resource management), and virtualized hosting (visibility and control). We identify design aspects and changes that helped CoralCDN succeed, yet also those that proved wrong for its current environment.