LTH-image


Abstract

RT-Xen: Real-Time Virtualization for the Cloud

Chenyang Lu, Washington University in St. Louis

Abstract:  

Presentation slides

Recent years have witnessed increasing demand of running real-time applications in the cloud. However, existing virtualization platforms cannot provide real-time performance guarantees to virtual machines. This talk will introduce RT-Xen, a real-time virtual machine scheduling framework in the Xen hypervisor. Built based on compositional real-time scheduling theory, RT-Xen realizes a suite of real-time schedulers spanning the design space including global and partitioned multi-core scheduling, fixed and dynamic priority, and different budget management schemes. Our experimental study shows RT-Xen schedulers deliver significant improvement in real-time performance over Xen’s existing credit scheduler and explores the tradeoff in real-time scheduler design in virtualized platforms. RT-Xen has been released as open-source software at https://sites.google.com/site/realtimexen/. Work is underway to incorporate RT-Xen in the Xen distribution and to integrate RT-Xen with the OpenStack cloud management system. RT-Xen represents a promising step toward real-time cloud computing for latency-sensitive applications.

Biography:  Chenyang Lu is a Professor of Computer Science and Engineering at Washington University in St. Louis. Professor Lu is Editor-in-Chief of ACM Transactions on Sensor Networks, Area Editor of IEEE Internet of Things Journal, and Associate Editor of Real-Time Systems. He also serves as Program Chair of premier conferences such as IEEE Real-Time Systems Symposium (RTSS 2012), ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS 2012) and ACM Conference on Embedded Networked Sensor Systems (SenSys 2014). Professor Lu is the author and co-author of over 100 research papers with over 10,000 citations and an h-index of 49. He received the Ph.D. degree from University of Virginia in 2001, the M.S. degree from Chinese Academy of Sciences in 1997, and the B.S. degree from University of Science and Technology of China in 1995, all in computer science. His research interests include real-time systems, wireless sensor networks and cyber-physical systems.