I'm a graduate student at the School of Computing, University of Utah. My current work extends the Xen virtualization platform with full-system deterministic replay capabilities. We use replay to implement dynamic analysis of complex software systems.

Recently I've started working on designing a practical, capability-based least authority infrastructure for virtualized environments.

I work as a research assistant for the Flux Research Group. John Regehr and Eric Eide advise my research.

I moved to Utah from Kiev, Ukraine, where I was a graduate student at the Institute for Applied System Analysis at the National Technical University of Ukraine "Kyiv Polytehnic Institute" (Complete education history). In Ukraine I worked with Leonid Ryzhyk. We were full of naive but interesting ideas. We spent several years working on the E1 distributed operating system project.

Some personal information. Complete work experience.

Curriculum Vitae [PDF]

Operating systems: new abstractions for building operating systems, virtualization, microkernels, distribution models, persistence, threading models, IPC mechanisms, applicability of lock-free algorithms to kernel structures.

Full-system deterministic replay: full-system deterministic replay, dynamic program analysis, replay-based performance and security analysis.

Access control: capabilities, practical access control in operating systems and virtualized environments, system design for principle of least authority.

Performance analysis as it exists today often degrades to performance debugging – a time-consuming, iterative, "measure and modify" procedure aimed at tuning the system. Analysis is used to provide hints about performance bottlenecks, but not a general understanding of system's performance.

Our work is aimed to provide an engineering foundation for development of formal, precise, and computationally intensive methods of performance analysis. We split analysis into two stages. First, we capture the complete run-time state of the system by means of full-system deterministic replay. Then, we invoke analysis on a complete copy of original execution off-line. We eliminate major restrictions on run-time performance analysis – complexity, nondeterminism, and lack of global comprehension of the entire system state. To enable performance analysis during replay, we extend traditional replay approaches with an ability to recreate a nonfunctional property of execution – performance.

Development of a replay debugging environment for distributed systems consisting of hundreds of machines. Our time-travel system will run along with an experiment launched in Emulab and capture original execution of an entire network of virtual machines. In case of an error, a researcher will be able to rollback execution of the network to the point before the crash and inspect its state or debug it with a traditional step-by-step debugger. On each node we replay entire OS along with its running processes.

Emulab includes more than 350 PC nodes. Some 1500 users run experiments of size 1-300 nodes, on a first-come first-served basis. Demand far exceeds capacity, so Emulab provides a weak form of time-sharing. We would like to schedule Emulab experiments similarly to how OS schedules its processes. The Emulab scheduler could preempt low-priority or idle experiments, save the full state of entire network, and replace it with other experiments. The goal is that swapout/swapin must be transparent to the experiment, and except for scheduling delays, transparent to users. In the context of Emulab, this means that we are able to preempt large long running experiments without compromising the correctness of experimental results.

Anton Burtsev, Kiran Srinivasan, Prashanth Radhakrishnan, Lakshmi N. Bairavasundaram, Kaladhar Voruganti, and Garth R. Goodson, NetApp, Inc. Fido: Fast Inter-Virtual-Machine Communication for Enterprise Appliances. In Proceedings of the 2009 USENIX Annual Technical Conference, San Diego, June 2009 [PDF] (Slides [PDF]).

Anton Burtsev, Prashanth Radhakrishnan, Mike Hibler, and Jay Lepreau. Transparent Checkpoints of Closed Distributed Systems in Emulab. In Proceedings of the Fourth ACM SIGOPS/EuroSys European Conference on Computer Systems, Nuremberg, Germany, April 2009 [PDF] (Slides [PDF]).

L.B. Ryzhyk, A.Y. Burtsev. Architectural design of E1 distributed operating system. System Research and Information Technologies international scientific and technical journal, October 2004, Kiev, Ukraine. [PDF].

Anton Burtsev, Eric Eide, John Regehr. A Replay-based Approach to Performance Analysis, 9th USENIX Symposium on Operating Systems Design and Implementation (OSDI '10) October, 2010 Vancouver, BC, Canada. Abstract [PDF], poster [PDF]

Anton Burtsev, Eric Eide, Mike Hibler, John Regehr. Benchmarks Can Make Sense, School of Computing Poster Competition March, 2010, Salt Lake City, Utah, USA. Poster [PDF]

Anton Burtsev, John Regehr. Operating Systems as Parallel Pipelines, School of Computing Poster Competition March, 2009, Salt Lake City, Utah, USA. Abstract [PDF], poster [PDF]

Anton Burtsev, Mike Hibler, Jay Lepreau. Aggressive Server Consolidation through Pageable Virtual Machines, 8th USENIX Symposium on Operating Systems Design and Implementation (OSDI '08) December, 2008 San Diego, CA, USA. Abstract [PDF], poster [PDF]

Anton Burtsev, Prashanth Radhakrishnan, Mike Hibler, Jay Lepreau. True Time-Sharing in Emulab through Preemption and Stateful Swapout, 4rd Symposium on Networked Systems Design and Implementation, Cambridge, May 2007. Abstract [PDF], poster [PDF]

Anton Burtsev, Prashanth Radhakrishnan, Mike Hibler, Jay Lepreau. Time Travel for Closed Distributed Systems, 3rd Symposium on Networked Systems Design and Implementation, San Jose, May 2006. Abstract [PDF], poster [PDF]

Taekwondo, tennis, skiing, jazz music, reading, painting, traveling.

Updated: June, 2010