Accounting for Memory Use , Cost , Throughput , and Latency

Conventional wisdom holds that reducing disk latency leads to higher disk utilization, maximizing disk utilization leads to higher throughput, employing a faster disk leads to better performance. All of this is true when building a conventional le or database system. In this paper we show that these principles can be misleading when applied to a media server. We examine a number of techniques that have been developed for maximizing disk bandwidth utilization in media servers, including disk arm scheduling and data placement ones. We show that, some disk latency reduction techniques can be counterproductive since memory, rather than disk, is the bottleneck in improving throughput. We present techniques for best memory use under diierent disk policies, and derive precise formulas for computing memory use. In addition, to precisely account for the design tradeoos between disk bandwidth and memory use, we propose a cost-based approach that focuses on minimizing the per-stream costs, including the disk and memory ones. Lastly, we study the worst-case initial latency of presentations, a factor that may be important in interactive systems. We present a novel technique for signiicantly reducing this initial latency under some disk scheduling schemes. Note to referees: This archival journal submission combines and integrates work presented at VLDB 97 4] and RIDE 98 5]. In addition to the prior published material, this paper contains new experimental results using data for the latest disks, as well as theorem proofs that were not included in the original papers.