Allocation strategies of multimedia data on disk arrays

Abstract

Recent technological advances will make it feasible to integrate multimedia data with computing. The data intensive nature of media types such as digital video and audio imposes two stringent requirements on the storage technology: (1) large storage capacity, and (2) a data transfer bandwidth that is sufficient to support the real-time retrieval of multi-media data. A disk array is one approach to improve the I/O performance by using multiple disks as a storage system. There are various ways in which to configure disk arrays, and various data allocation strategies also exist. Each gives a different performance from the others, depending on the type of workload. In this paper, we propose various allocation strategies of multimedia data on disk arrays, and evaluate their performance by simulation. Results show that the strategy of storing media blocks so they are synchronized contiguously has the best performance. Unfortunately, it is almost impossible to carry out the strategy when a number of users are involved. The second best strategy is the case where media of the same type take disk modules exclusively. Furthermore, the results lead us to conclude that, for most multimedia applications, it is better to pursue concurrency than parallelism in disk array organization.