Thursday, February 15 , 2007
12:00 pm - 1:00 pm
Wean Hall 8220
Enabling What-if Explorations in Distributed Systems
With a large percentage of total system cost going to system administration tasks, self-management remains a difficult and important goal in systems. As a step towards the self-management vision, I will present a framework I have developed that enables systems to be self-predicting and answer ``what-if'' questions about their behavior with little or no administrator involvement. I have prototyped the framework in a Resource Advisor module inside two real systems: Microsoft's SQL Server database and the Ursa Minor storage system at Carnegie Mellon University. The Resource Advisor helps with upgrade and data placement decisions and provides what-if interfaces to external administrators (and internal tuning modules). The Resource Advisor is based on efficient system behavioral models that enable robust predictions in multi-tier systems.
Eno Thereska is a PhD student working with Prof. Greg Ganger in the area of autonomic systems. He's graduating this coming summer and this is a practice job talk.
or visit http://www.pdl.cmu.edu/SDI/