Real-Time Parallel IO Stream Scheduling

ERTUĞ Ö., Kallahalla M., Varman P. J.

Proceedings of the Fifth Joint Conference on Information Sciences, JCIS 2000, Atlantic City, NJ, United States Of America, 27 February - 03 March 2000, vol.5, pp.441-444, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 5
  • City: Atlantic City, NJ
  • Country: United States Of America
  • Page Numbers: pp.441-444
  • Gazi University Affiliated: Yes

Abstract

We introduce a framework for real-time I/O scheduling for multiple-disk parallel I/O systems. The framework is used to model a video server delivering VBR encoded video data with real-time requirements. The video streams are assumed to be stored in CDL format and distributed across multiple disks. We present a novel algorithm RT-OPT for optimally prefetching blocks into the server buffer. We show that for any fixed disk-head scheduling policy, RT-OPT is guaranteed to produce a feasible schedule, in which all blocks meet their deadlines, if one exists. Simulations show that the number of clients supported by RT-OPT is superior to intuitive algorithms like GREED-EDF that aggressively keep the disks busy fetching in order of deadlines.