Optimizing Configuration for Hierarchical Storage Based Continuous Media Server

Recent advances in computing and communication technologies have made it technically feasible and economically viable to provide on-line access to a variety of information services over high speed networks. Particularly, convergence of various technological factors, namely in network access and in video coding and transmission, have recently brought a rapid growth of interest in on-line access to multimedia services. The problem of largescale provision of services has several implications for the design of a storage server. Voluminous nature of a multimedia file is one of the primary reasons which makes the design of the server non trivial. With MPEG-2 compression technique a movie file of 110 min length requires more than 3 G bytes of storage space. Storing thousands of files of this size on a disk subsystem requires huge amounts of disk space. According to user surveys[7], file-access frequency is strictly biased in favor of a small number of popular titles, while the rest of the files are rarely accessed in commercial video rental. This characteristic of the user-access pattern enables the storage architecture designer to exploit the hierarchical storage structure in managing a large volume of information. The advantage of using hierarchical storage architecture is to exploit the popularity or hotness of a file and assign space the appropriate storage hierarchy to each file, thereby maximizing the cost-performance ratio. The efficiency of hierarchical storage architecture is maximized when the capacity of each hierarchy is well balanced and the behavior of each storage hierarchy is well harmonized. Thus, in configuring hierarchical storage, these system parameters have to be carefully taken into account. From the server’s point of view, maximizing throughput is primary concern in various aspects of the design. Throughput can be thought as the number of requests which can be handled or serviced by the server per unit time. When user request needs to be serviced immediately, the number of requests which can be handled per unit time, throughput is inversely proportional to the probability that the incoming request is blocked. Thus, Blocking probability is an important concern in achieving a desired cost-effectiveness. In hierarchical storage architecture which consists of tertiary storage and secondary storage, the request blocking can be due to congestion in tertiary storage or due to congestion in secondary storage In this work, the effort is concentrated on finding a minimum amount of storage resources for each hierarchy to achieve a given throughput. Storage capacity and bandwidth capacity of a unit storage device, e.g. a disk drive, a tape drive is fixed. Blocking probability is a metric for throughput.