On Application-level Approaches to Avoiding TCP Throughput Collapse in Cluster-Based Storage Systems. [pdf]
Elie Krevat, Vijay Vasudevan, Amar Phanishayee, David Andersen, Gregory Ganger, Garth Gibson, Srinivasan Seshan. In the Proceedings of the ACM/IEEE Petascale Data Storage Workshop, Supercomputing (PDSW, SC 07). [November 2007].
Technical Reports.
FAWN: A Fast Array of Wimpy Nodes. [pdf]
David G. Andersen, Jason Franklin, Amar Phanishayee, Lawrence Tan, and Vijay Vasudevan. Carnegie Mellon University Parallel Data Laboratory Technical Report, CMU-PDL-08-108 (May, 2008).
Project Homepage: FAWN
Measurement and Analysis of TCP Throughput Collapse in Cluster-Based Storage Systems. [pdf], [poster]
Amar Phanishayee, Elie Krevat, Vijay Vasudevan, David Andersen, Gregory Ganger, Garth Gibson, Srinivasan Seshan. Carnegie Mellon University Parallel Data Lab Technical Report, CMU-PDL-07-105 (September, 2007). Note: Refer to the paper in FAST 2008 for the latest information on this project.
Project: Quicksilver. This is primarily Krzystof Ostrowski's work. I was invloved in evaluating the scalability of JGroups for comaprison studies with Quicksilver.
QuickSilver Scalable Multicast. [pdf]
Krzysztof Ostrowski, Ken Birman, and Amar Phanishayee. Cornell University Technical Report, TR2006-2063 (April, 2006).
The Power of Indirection: Achieving Multicast Scalability by Mapping Groups to Regional Underlays. [pdf]
Krzysztof Ostrowski, Ken Birman and Amar Phanishayee. Cornell University Technical Report, TR2006-2064 (November, 2005).