> cat research_statement
My research is developing general and scalable techniques for exploring the runtime and historic file system state of virtual machines (VMs). My specific focus is on performant solutions which incur low overhead, and scale well to tens of thousands of running instances or stored virtual disk snapshots. I develop two techniques exposing this state at scale: introspection, and retrospection.
Introspection means the capability to inspect virtual disk state while it is mutating—during VM execution.
Retrospection is a term meaning the capability to search and investigate frozen historic state of virtual disks in a central store. I am actively extending my work to VM memory.
Combined with the centralization of cloud computing, my work enables the development of previously impossible troubleshooting tools which provide insight into computational state across multiple executing VM instances, and enable tracking of the evolution of state in clouds.
> cat collaborators
I am lucky to have active collaboration with an excellent set of researchers, both at CMU and also external to CMU. At CMU I collaborate predominantly with:
- Mahadev Satyanarayanan
- Dave Andersen
- Srini Seshan
- Jan Harkes
- Benjamin Gilbert
- Adam Goode [Now at Google Pittsburgh]
- Kiryong Ha
- Erik Zawadzki
- Alok Shankar
- Athula Balachandran
During my tenure as a grad student, and for a summer internship in 2011, I have collaborated with researchers at IBM on distributed systems (cloud) research:
My forays into mobile research have led me to collaborate with researchers at Rice University:Duke University:
Other collaborators include:
> cat history
I come from the University of Virginia (SEAS '09, BS CS) where I was involved in distributed computing research. While at UVA, I worked and interacted predominantly with:online).