RT-Xen: towards real-time hypervisor scheduling in xen

  • Authors:
  • Sisu Xi;Justin Wilson;Chenyang Lu;Christopher Gill

  • Affiliations:
  • Washington University in St. Louis, St. Louis, MO, USA;Washington University in St. Louis, St. Louis, MO, USA;Washington University in St. Louis, St. Louis, MO, USA;Washington University in St. Louis, St. Louis, MO, USA

  • Venue:
  • EMSOFT '11 Proceedings of the ninth ACM international conference on Embedded software
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

As system integration becomes an increasingly important challenge for complex real-time systems, there has been a significant demand for supporting real-time systems in virtualized environments. This paper presents RT-Xen, the first real-time hypervisor scheduling framework for Xen, the most widely used open-source virtual machine monitor (VMM). RT-Xen bridges the gap between real-time scheduling theory and Xen, whose wide-spread adoption makes it an attractive platform for integrating a broad range of real-time and embedded systems. Moreover, RT-Xen provides an open-source platform for researchers and integrators to develop and evaluate real-time scheduling techniques, which to date have been studied predominantly via analysis and simulations. Extensive experimental results demonstrate the feasibility, efficiency, and efficacy of fixed-priority hierarchical real-time scheduling in RT-Xen. RT-Xen instantiates a suite of fixed-priority servers (Deferrable Server, Periodic Server, Polling Server, and Sporadic Server). While the server algorithms are not new, this empirical study represents the first comprehensive experimental comparison of these algorithms within the same virtualization platform. Our empirical evaluation shows that RT-Xen can provide effective real-time scheduling to guest Linux operating systems at a 1ms quantum, while incurring only moderate overhead for all the fixed-priority server algorithms. While more complex algorithms such as Sporadic Server do incur higher overhead, none of the overhead differences among different server algorithms are significant. Deferrable Server generally delivers better soft real-time performance than the other server algorithms, while Periodic Server incurs high deadline miss ratios in overloaded situations.