I am a second year Ph.D. student in the UC Berkeley NetSys Lab, advised by Sylvia Ratnasamy. I am broadly interested in networking, computer systems, and cloud computing. My current research centers around supporting lower latency in compute clusters. I am interested in scalable cluster scheduling that can handle the high task turnover rate of sub-second tasks, and in the performance benefits of using short tasks for all jobs (even long-running batch jobs).
The Case for Tiny Tasks in Compute Clusters Kay Ousterhout, Aurojit Panda, Joshua Rosen, Shivaram Venkataraman, Reynold Xin, Sylvia Ratnasamy, Scott Shenker, Ion Stoica HotOS 2013 (to appear)
Sparrow: Scalable Scheduling for Sub-Second Parallel Jobs Kay Ousterhout, Patrick Wendell, Matei Zaharia, Ion Stoica UC Berkeley EECS 2013