A BUFFER-INVENTORY-BASED DYNAMIC SCHEDULING ALGORITHM FOR MULTIMEDIA-ON-DEMAND SERVERS

We present a producer-consumer model of multimedia-on-demand (MOD) ser vers. The producer retrieves media data from a disk and places it into a set of buffers, while the consumer sends out the data in the buffer s to the users, We develop for the producer a buffer-inventory-based d ynamic scheduling (BIDS) algorithm that guarantees non-zero inventory and non-overflow of data in the buffers to meet the continuity require ment and no-loss of data for each media stream. The algorithm can deal with heterogeneous me dia streams as well as the transient circumstan ces upon service completions and arrivals of new requests. To smooth o ut the impact of bursty data of variable-bit-rate media streams and th erefore increase the maximum admissible load of requests, we also intr oduce into the scheduling scheme a time-scale-dependent peak consumpti on rate and a virtual cycle time. Based on BIDS, an effective admissio n control mechanism can be easily established by checking two simple c onditions respectively on the overall system load and buffer size. Our algorithm is very easy to implement. Experiments carried out with an actual disk system and real video stream data verify that it is more r obust compared to static scheduling algorithms previously proposed in the literature, especially when handling variable-bit-rate media strea ms.