Email: jeffra / cs brown edu
Office: 334 CIT
115 Waterman Street
Computer Science Department
Providence, RI 02912
I am a second-year Ph.D. student advised by Rodrigo Fonseca,
primarily interested in networks, distributed systems, and security. I am supported by an
NSF Graduate Research Fellowship.
I completed my undergrad at the University of Washington where I studied computer science. During my time at UW I primarily worked with Justin Cappos on topics related to sandbox security and API Write-Once-Run-Anywhere verification.
I also worked on the GENI supported peer-to-peer testbed called Seattle.
More details can be found in my CV.
- 2014-04: Presenting a poster on low-latency network monitoring at NSDI '14 via a generous travel grant from USENIX.
- 2014-03: Poster judge at NEUCS '14.
- 2014-03: I will be spending the summer at VMware in the NSX (i.e. Nicira) group.
- 2014-02: I will be presenting our paper "Low-latency Network Monitoring via Oversubscribed Port Mirroring" at the Open Networking Summit's Research Track.
- 2013-12: Visiting Nathan Bishop Middle School to help students with an Hour of Code.
- 2013-09: Attending IMC '13 via a generous travel grant by the NSF.
- 2013-06: NSF Graduate Research Fellowship Awardee (2013), Brown blog post
- 2013-04: Poster judge at NEUCS '13. Sadly, the event was canceled.
I will be at IBM Research in Austin working with Colin Dixon this summer.
Low-latency Network Monitor and Control MethodsSoftware-defined networking introduces the possibility of building self-tuning networks that constantly monitor network conditions and react rapidly to important events such as network congestion. Unfortunately, state-of-the-art monitoring mechanisms for conventional networks require hundreds of milliseconds to seconds to extract global network state like global link utilization or the identity of "elephant" flows. My work in this area looks at improved techniques for measuring and controlling high-speed 10GbE or higher data center networks. This is ongoing work with my colleagues at IBM Research and Brown.
Network Impact of DISC FrameworksData Intensive Scalable Compute (DISC) frameworks such as Hadoop and Spark are becoming increasingly important tools for many institutions. Inherently the network is a key factor in the performance of these frameworks, yet this interaction is still poorly understood because of the growing complexity of applications and large shared data center infrastructures. My work in this area is a systematic study of the impact between the network and the end-to-end performance of DISC framework applications.
Publications, Posters, etc.
- A Low-Latency Network Monitoring Platform Jeff Rasley, Brent Stephens, Colin Dixon, Eric Rozner, Wes Felter, Kanak Agarwal, John Carter, Rodrigo Fonseca. Poster to appear at the 11th USENIX Symposium on Networked Systems Design and Implementation (NSDI 2014). Seattle, WA, 2014 [poster]
- Low-latency Network Monitoring via Oversubscribed Port Mirroring Jeff Rasley, Brent Stephens, Colin Dixon, Eric Rozner, Wes Felter, Kanak Agarwal, John Carter, Rodrigo Fonseca. Paper at the Open Networking Summit. Santa Clara, CA, March 2014 [pdf] [slides]
- Runtime Verification of Portable Programming Interfaces Jeff Rasley. Honors Thesis. Computer Science and Engineering, University of Washington, June 2011
- Seattle: The Internet as a Testbed. Jeff Rasley, Monzur Muhammad, Alex Hanson, Sebastian Morgan, Alan Loh, Justin Cappos. Poster at the 8th USENIX Symposium on Networked Systems Design and Implementation (NSDI 2011). Boston, MA, 2011
- Retaining Sandbox Containment Despite Bugs in Privileged Memory-Safe Code Justin Cappos, Armon Dadgar, Jeff Rasley, Justin Samuel, Ivan Beschastnikh, Cosmin Barsan, Arvind Krishnamurthy, and Thomas Anderson. The 17th ACM Conference on Computer and Communications Security (CCS 2010). Chicago, IL, 2010 [pdf]