1/11: Send me your email address, even if you are only going to be attending periodically.
1/11: Feel free to skim the second Legion paper (the 1998 tech report); I had forgotten how long it was
The overwhelming success of the World Wide Web has placed tremendous demands on the infrastructure for supporting wide-area services and applications. These demands introduce new scaling issues for the servers, clients, networks, and protocols used to provide Web services. As these services grow more complex, identifying, understanding, and addressing key system performance bottlenecks continues to be a challenge. At the same time, the growth and evolution of the Web presents unparalleled opportunities for developing new services and applications. E-commerce continues to rise, we are witnessing increasing deployment and use of streaming multimedia architectures, wide-area services are being extended into the mobile and wireless arenas, and Web-based mail systems have given us a taste for highly-available, platform- and location-independent services.
Together, the demands and opportunities of the Web present exciting challenges for operating and distributed systems research in wide-area systems such as the Web. This class will survey current research in this area, including work in wide-area caching, prefetching, replication, naming, distributed computation, scalable servers, security, and communication protocols.
A primary goal of this class is to provide the background necessary for doing research on these topics. We will read and evaluate research papers selected from the literature, and class will consist of lecture and discussion of these papers. Students will be asked to evaluate the papers as a basis for discussion, but there will be no written assignments or exams. Those enrolled for full credit will also do a class project in small groups. A complete schedule and reading list for the term will be given on the first day of class, but send me mail if you have questions before then.