, Volume 30, Issue 1-2, pp 31-53

Design, Implementation and Evaluation of a Real-Time Active Content Distribution Service

Rent the article at a discount

Rent now

* Final gross prices may vary according to local VAT.

Get Access

Abstract

The phenomenal growth of the world-wide web has made it the most popular Internet application today. Web caching and content distribution services have been recognized as valuable techniques to mitigate the explosion of web traffic. An increasing fraction of web traffic today is dynamically generated and therefore intrinsically difficult to replicate or cache using present static approaches. Scalable delivery of such active content poses a myriad of challenges, including content replication, update propagation, and consistency management. This paper makes two contributions: it (1) describes a scalable architecture for transparent demand-driven distribution of active content; and (2) presents a system that can provide real-time delay guarantees on content access. Our approach involves migrating the scripts which generate dynamic web traffic, and their data, from the origin servers to active content distribution proxies nearest to the clients. We also present mechanisms on these proxies to enforce real-time delay guarantees for client requests. Our system is implemented and deployed on Planetlab (2004), a real-world distributed Internet testbed. Experimental data show that significant improvements are observed in effective throughput and client response time, and that delay bounds on content access can be guaranteed with a very high probability.

Chengdu Huang received his B.Sc. degree from Tongji University, China, in 2000, and his Master of Computer Science degree from Department of Computer Science, University of Virginia, in 2004. He is currently a Ph.D. candidate in University of Virginia. His research interests include Content Distribution Networks, peer-to-peer systems, and QoS guarantees in server systems.
Seejo Sebastine received his Bachelor of Engineering from PSG College of technology, Indian, in 2000, and his Master of Computer Science degree from Department of Computer Science, University of Virginia, in 2001. He is now working with Hughs Network Systems at Germantown, MD.
Tarek Abdelzaher received his B.Sc. and M.Sc. degrees in Electrical and Computer Engineering from Ain Shams University, Cairo, Egypt, in 1990 and 1994 respectively. He received his Ph.D. from the University of Michigan in 1999. Since 1999 he has been an Assistant Professor at the University of Virginia where he founded the Software Predictability Group. He has authored/coauthored more than 60 refereed publications. He was Guest Editor for the Journal of Computer Communications and the Journal of Real-Time Systems, and is on the editorial boards of real-time and embedded systems journals. He served on numerous Program Committees, and held several organizing positions including Poster Chair of ICDCS 2003, Work-in-Progress Chair of RTSS 2003, Program Chair of RTAS 2004, and General Chair of RTAS 2005. He is a patent holder on Adaptive Web Systems, an IEEE and ACM member, and an NSF Career award recepient. Tarek’s research interests include QoS provisioning, real-time computing, operating systems, computer networking, and sensor networks. He is particularly interested in developing and experimentally validating new foundations for performance guarantees in highly dynamic unpredictable software systems, ranging from open high-performance Internet applications to low-power sensor networks and embedded systems.