UCSC-CRL-93-06: SCHEDULING REAL-TIME DISK TRANSFERS FOR CONTINUOUS MEDIA APPLICATIONS

01/01/1993 09:00 AM
Computer Science
We study how continuous media data can be stored and accessed in the Swift distributed I/O architecture. We provide a scheme for scheduling real-time data transfers that satisfies the strict requirements of continuous media applications. Our scheme allows large data objects to be stored and retrieved concurrently from multiple disks so as to satisfy the high data rate requirements which are typical of real-time video and audio data. To do this, data transfer requests are split into smaller requests which are then handled by the various components of Swift. We study on-line algorithms that respond to a data request by promising to either satisfy or reject it. Each response must be made before the next request is seen by the algorithm. We discuss two different performance measures to evaluate such algorithms and show that no on-line algorithm can optimize these criteria to less than a constant fraction of the optimal. Finally, we propose an algorithm for handling such requests on-line and the related data structures.

UCSC-CRL-93-06