Developing new tools to analyze network data is often a complex and error-prone process. Current practices require developers to possess an in-depth understanding of the original data sets and to develop ad-hoc software tools to first extract the relevant information from the data and then implement the internals of the new algorithm. This development process results in long delays during the analysis of the data and in the production of software that is often hard to reuse, debug or optimize. We present the design and implementation of CoMo, a system for fast prototyping network data mining applications. CoMo provides an abstraction layer both for the network data as well as for the hardware architecture used to collect and process the data. This allows developers to focus on the correctness of the implementation of their analysis tools while the system makes the tool amenable to optimization when running on different hardware architectures. In this talk we discuss CoMo's design challenges, our solution to address them and evaluate the resulting software in terms of performance, flexibility and ease of use.

[slides]

Gianluca Iannaccone is a Research Scientist at the Intel Research lab in Berkeley. His research interests lie in the area of networked systems. He is currently active in the RouteBricks project that aims at building a scalable and programmable high speed router out of a cluster of Intel servers. He is also Chief Architect for a newly formed product group under the New Business Initiatives group at Intel. The new product will build around CoMo, a fast prototyping platform for network data mining applications, and deliver a platform for the small and medium businesses. Gianluca joined Intel Research, Cambridge, UK in September 2003 and moved to Berkeley, CA in January 2007. Prior to Intel, Gianluca worked as research scientist at Sprint Advanced Technology Laboratories in Burlingame, CA where his work focused on the characterization and modeling of network traffic and on the analysis of fault management techniques for large IP networks. He received his PhD from the University of Pisa, Italy in 2001.