Experiences with CoralCDN: A five-year operational view

Michael J. Freedman

Experiences with CoralCDN: A five-year operational view

Research output: Contribution to conference › Paper › peer-review

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.

Original language	English (US)
Pages	95-110
Number of pages	16
State	Published - Jan 1 2019
Event	7th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2010 - San Jose, United States Duration: Apr 28 2010 → Apr 30 2010

Conference

Conference	7th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2010
Country/Territory	United States
City	San Jose
Period	4/28/10 → 4/30/10

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Control and Systems Engineering

Cite this

@conference{fe499e9a77f845de903c003adbf27d6c,

title = "Experiences with CoralCDN: A five-year operational view",

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.",

author = "Freedman, {Michael J.}",

year = "2019",

month = jan,

day = "1",

language = "English (US)",

pages = "95--110",

note = "7th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2010 ; Conference date: 28-04-2010 Through 30-04-2010",

}

TY - CONF

T1 - Experiences with CoralCDN

T2 - 7th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2010

AU - Freedman, Michael J.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85076737593&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076737593&partnerID=8YFLogxK

M3 - Paper

SP - 95

EP - 110

Y2 - 28 April 2010 through 30 April 2010

ER -

Experiences with CoralCDN: A five-year operational view

Abstract

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this