Run-time optimization of heterogeneous media access in a multimedia server

Abstract

Discrete media (DM) data throughput is vital to systems that need to support the heterogeneity and variety of data found in interactive hypermedia and digital library applications. Therefore, a multimedia server's ability in delivering a high DM data throughput without degrading its CM data throughput deserves more attention. In this paper, we address this issue by optimizing the use of disk bandwidth spent on CM service at run-time and redirecting the saved bandwidth to service DM requests. Based on a new cost model of disk access incurred in CM service, we formulate strategies to control the size of each disk read at run time. These strategies improve the efficiency of each disk access and improve the DM data throughput of a multimedia server, without jeopardizing the CM throughput. Through experimental evaluations, the improvements achieved are demonstrated. Furthermore, efficient control of the allocation of disk bandwidth between DM and CM services over a wide range is also demonstrated.

A Cost-Based Admission Control Algorithm for Digital Library Multimedia Systems Storing Heterogeneous Objects

“…The sizes of image and text objects requested are randomly generated from their respective ranges. For the video clips, we take a trace file of the movie Star Wars which consists of 7200 groups 5 Other T SR values were also used with the results exhibiting a similar trend and thus they are not reported. For a classic tradeoff analysis between the magnitude of T SR versus the memory requirement, and the number of requests admissible, see [9].…”

“…(i) Video-First: the video-first algorithm always gives the highest priority to video requests (an example of which can be found in [5]). Under this algorithm, all resources are allocated to video requests with the leftover bandwidth being used to serve image and text requests.…”

“…Less attention has been paid to how to service mixed workload objects effectively for multimedia servers designed to provide online digital library multimedia services [2,3,4,5].…”

“…While the design of level 2 class-specific schedulers was discussed in detail, no discussion was given on how the class-independent scheduler at level 1 can adapt to workload changes to reallocated disk bandwidth at run time. In another work, To and Hamidzadeh [5] suggested trading off continuous media (CM) throughput for discrete media (DM) throughput by using the CM-to-DM throughput redirection ratio as a performance metric. They suggested ways of trading CM throughput with DM throughput.…”

Adaptive QoS Control Based on Benefit Optimization for Video Servers Providing Differentiated Services

“…The goal is either to reduce the overall cost per request or to maximize the maximum number of requests the system is able to service simultaneously with statistical or absolute QoS guarantees. There also have been research efforts to deal with mixed workloads, again by means of admission control and disk scheduling mechanisms [13,14]. This paper also concerns with the server end design.…”