Sunghwan Ihm will present his research seminar/general exam on Wednesday May 21 at 10AM in room 402. The members of his committee are: Vivek Pai (advisor), Jennifer Rexford, and Mike Freedman. Everyone is invited to attend his talk, and those faculty wishing to remain for the oral exam following are welcome to do so. His abstract and reading list follow below. ------------------------------------------------- [Abstract] In the developing world, Internet access is often expensive, low-bandwidth, and high latency. The situation gets even worse since even low-capacity links are shared by many people. However, there may also be much redundant network traffic due to the sharing. Wide-area network (WAN) acceleration is a protocol-independent approach to caching redundant traffic to avoid sending duplicate data over slow links. Among the many techniques for eliminating redundancy, content-based naming (CBN) scheme is one of the most effective approaches. CBN breaks data into position-independent chunks based on its content, and names them with their hash values, so that they can be shared across different transfers. While recent CBN-based systems have shown the effectiveness of this approach, they are often designed to be point-to-point systems, and do not take advantage of groups of local users. Further, they are often targeted to specific environments, and have design-based limits on performance. In this work, we propose Waprox, a high-performance WAN accelerator using CBN. Waprox uses a novel multi-resolution chunking (MRC) scheme to address the tradeoff between chunk size and performance. The intuition is to use small chunk sizes when needed to eliminate redundancy, but use larger chunk sizes when possible, in order to improve performance. We demonstrate the effectiveness of MRC by a trace-based simulation analysis. We also implement a prototype of Waprox, and show that it consumes 18% less bandwidth while having 21% higher throughput. [Text Book] L. Peterson, and B. Davie, Computer Networks: A Systems Approach, 4th Edition, Morgan Kaufmann Publishers, March 2007. [Papers] 1. N. T. Spring and D. Wetherall. A protocol-independent technique for eliminating redundant network traffic. In SIGCOMM, Aug. 2000. 2. A. Muthitacharoen, B. Chen, and D. Mazieres. A low-bandwidth network file system. In Proc. 18th SOSP, pages 174--187, Oct. 2001. 3. V. S. Pai, M. Aron, G. Banga, M. Svendsen, P. Druschel, W. Zwaenepoel, and E. Nahum. Locality-Aware Request Distribution in Cluster-based Network Servers. In Proceedings of the 8th ACM Conference on Architectural Support for Programming Languages and Operating Systems, San Jose, CA, Oct. 1998. 4. L. Wang, V. Pai, and L. Peterson. The effectiveness of request redirection on CDN robustness. In Proceedings of The Fifth Symposium on Operating Systems Design and Implementation (OSDI'02), Boston, MA, December 2002. 5. J. C. Mogul, Y. M. Chan, and T. Kelly. Design, implementation, and evaluation of duplicate transfer detection in HTTP. In Proc. First Symposium on Networked Systems Design and Implementation (NSDI), San Francisco, CA, Mar. 2004. 6. H. Pucha, D. G. Andersen, and M. Kaminsky. Exploiting similarity for multi-source downloads using file handprints. In Proceedings of the 4th USENIX/ACM Symposium on Networked Systems Design and Implementation(NSDI'07), 2007. 7. N. Tolia, M. Kaminsky, D. G. Andersen, and S. Patil. An architecture for Internet data transfer. In Proc. 3rd Symposium on Networked Systems Design and Implementation (NSDI), San Jose, CA, May 2006. 8. S. Annapureddy, M. J. Freedman, and D. Mazières. Shark: Scaling file servers via cooperative caching. In Proc. 2nd USENIX NSDI, Boston, MA, May 2005. 9. R. CHAKRAVORTY, A. CLARK AND I. PRATT. Optimizing Web Delivery over Wireless Links: Design, Implementation and Experiences. IEEE Journal of Selected Areas in Communications (JSAC) 10. S. Rhea, K. Liang, and E. Brewer. Value-based web caching. In Proc. of the 12th Int. World Wide Web Conference, May 2003.