Virtualization is a key technology for safeguarding security and fault-tolerance purposes in networked systems. Hardware support for virtualization allows subsystem isolation to be achieved that can greatly limit the damage caused by an attacker or by hardware and software failures. This project studies two issues that address severe limitations on current virtualization technology: to properly support a real-time operating system, and to allow for recursive virtualization in the design of the hypervisor, the system layer that enforces isolation. The project is conducting a detailed study of a design framework whereby the hypervisor is capable of running hard real-time guests and also capable of participating in recursive virtualization. More importantly, the transparency of the hypervisor is maintained to support hierarchical virtualization, so that off-the-shelf commercial operating systems can be run without having to modify their code. For non-preemptive real-time resource scheduling, various resource partitioning algorithms and their implications on meeting timing constraints are considered, including I/O needs. The goal of this project is a hierarchical hypervisor that is real-time ready. The result of this project is expected to impact the successful deployment of many types of real-time embedded applications that are increasingly networked. These applications span transportation systems, medical devices, assisted living for the elderly, environmental monitoring, military systems and others too many to mention. Success in this project is expected to provide the foundational technologies for deploying secure and fault-tolerant sensor/actuator networks that will benefit society at large. Technical insights from this project are being incorporated into university computer science classes.

Agency
National Science Foundation (NSF)
Institute
Division of Computer and Network Systems (CNS)
Application #
0719925
Program Officer
D. Helen Gill
Project Start
Project End
Budget Start
2007-08-01
Budget End
2010-07-31
Support Year
Fiscal Year
2007
Total Cost
$240,000
Indirect Cost
Name
University of Texas Austin
Department
Type
DUNS #
City
Austin
State
TX
Country
United States
Zip Code
78712