Lavanya Ramakrishnan
Biographical Sketch
Lavanya Ramakrishnan is an Alvarez Postdoctoral Fellow at Lawrence Berkeley National Lab. She is currently working on the Magellan project, evaluating cloud computing for science. Previously, she has explored resource and workflow management for scientific applications in distributed environments. She completed her doctoral degree from Indiana University, Bloomington in June 2009. Previously, she was a research staff member at MCNC and the Renaissance Computing Institute (RENCI) in North Carolina. She has a master’s degree in Computer Science from Indiana University and a bachelor’s degree in Computer Engineering from the University of Mumbai in India.
Conference Papers
Dan Gunter, Shreyas Cholia, Anubhav Jain, Michael Kocher, Kristin Persson, Lavanya Ramakrishnan, Shyue Ping Ong, Gerbrand Ceder, “Community Accessible Datastore of High-Throughput Calculations: Experiences from the Materials Project”, 5th IEEE Workshop on Many-Task Computing on Grids and Supercomputers (MTAGS) 2012, November 12, 2012,
Ghoshal, Devarshi and Canon, Richard Shane and Ramakrishnan, Lavanya, “Understanding I/O Performance of Virtualized Cloud Environments”, The Second International Workshop on Data Intensive Computing in the Clouds (DataCloud-SC11), 2011,
- Download File: ioperformance.pdf (pdf: 174 KB)
We compare the I/O performance using IOR benchmarks on two cloud computing platforms - Amazon and the Magellan cloud testbed.
Lavanya Ramakrishnan, Richard Shane Canon, Krishna Muriki, Iwona Sakrejda, and Nicholas J. Wright., “Evaluating Interconnect and Virtualization Performance for High Performance Computing”, Proceedings of 2nd International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems (PMBS11), 2011,
- Download File: pmbs11.pdf (pdf: 441 KB)
In this paper we detail benchmarking results that characterize the virtualization overhead and its impact on performance. We also examine the performance of various interconnect technologies with a view to understanding the performance impacts of various choices. Our results show that virtualization can have a significant impact upon performance, with at least a 60% performance penalty. We also show that less capable interconnect technologies can have a significant impact upon performance of typical HPC applications. We also evaluate the performance of the Amazon Cluster compute instance and show that it performs approximately equivalently to a 10G Ethernet cluster at low core counts.
Lavanya Ramakrishnan, Piotr T. Zbiegel, Scott Campbell, Rick Bradshaw, Richard Shane Canon, Susan Coghlan, Iwona Sakrejda, Narayan Desai, Tina Declerck, Anping Liu, “Magellan: Experiences from a Science Cloud”, Proceedings of the 2nd International Workshop on Scientific Cloud Computing, ACM ScienceCloud '11, Boulder, Colorado, and New York, NY, 2011, 49 - 58,
- Download File: P1871.pdf (pdf: 318 KB)
Keith Jackson, Lavanya Ramakrishnan, Karl Runge, and Rollin Thomas, “Seeking Supernovae in the Clouds: A Performance Study”, ScienceCloud 2010, the 1st Workshop on Scientific Cloud Computing, Chicago, Illinois, June 2010,
Keith R. Jackson, Ramakrishnan, Muriki, Canon, Cholia, Shalf, J. Wasserman, Nicholas J. Wright, “Performance Analysis of High Performance Computing Applications on the Amazon Web Services Cloud”, CloudCom, Bloomington, Indiana, January 1, 2010, 159-168,
Lavanya Ramakrishnan, R. Jackson, Canon, Cholia, John Shalf, “Defining future platform requirements for e-Science clouds”, SoCC, New York, NY, USA, 2010, 101-106,
Presentation/Talks
Lavanya Ramakrishnan & Shane Canon, NERSC, Hadoop and Pig Overview, October 2011,
The MapReduce programming model and its open source implementation Hadoop is gaining traction in the scientific community for addressing the needs of data focused scientific applications. The requirements of these scientific applications are significantly different from the web 2.0 applications that have traditionally used Hadoop. The tutorial will provide an overview of Hadoop technologies, discuss some use cases of Hadoop for science and present the programming challenges with using Hadoop for legacy applications. Participants will access the Hadoop system at NERSC for the hands-on component of the tutorial.
Reports
Katherine Yelick, Susan Coghlan, Brent Draney, Richard Shane Canon, Lavanya Ramakrishnan, Adam Scovel, Iwona Sakrejda, Anping Liu, Scott Campbell, Piotr T. Zbiegiel, Tina Declerck, Paul Rich, “The Magellan Report on Cloud Computing for Science”, U.S. Department of Energy Office of Science, Office of Advanced Scientific Computing Research (ASCR), December 2011,
- Download File: MagellanFinalReport.pdf (pdf: 10 MB)
