DocumentCode
416107
Title
Scalable multimedia disk scheduling
Author
Mokbel, Mohamed F. ; Aref, Walid G. ; Elbassioni, Khaled ; Kamel, Ibrahim
Author_Institution
Dept. of Comput. Sci., Purdue Univ., West Lafayette, IN, USA
fYear
2004
fDate
30 March-2 April 2004
Firstpage
498
Lastpage
509
Abstract
A new multimedia disk-scheduling algorithm, termed Cascaded-SFC, is presented. The Cascaded-SFC multimedia disk scheduler is applicable in environments where multimedia data requests arrive with different quality of service (QoS) requirements such as real-time deadline and user priority. Previous work on disk scheduling has focused on optimizing the seek times and/or meeting the real-time deadlines. The Cascaded-SFC disk scheduler provides a unified framework for multimedia disk scheduling that scales with the number of scheduling parameters. The general idea is based on modeling the multimedia disk requests as points in multiple multidimensional subspaces, where each of the dimensions represents one of the parameters (e.g., one dimension represents the request deadline, another represents the disk cylinder number, and a third dimension represents the priority of the request, etc.). Each multidimensional subspace represents a subset of the QoS parameters that share some common scheduling characteristics. Then the multimedia disk scheduling problem reduces to the problem of finding a linear order to traverse the multidimensional points in each subspace. Multiple space-filling curves are selected to fit the scheduling needs of the QoS parameters in each subspace. The orders in each subspace are integrated in a cascaded way to provide a total order for the whole space. Comprehensive experiments demonstrate the efficiency and scalability of the Cascaded-SFC disk scheduling algorithm over other disk schedulers.
Keywords
disc storage; multimedia servers; quality of service; scheduling; Cascaded-SFC scheduler; QoS; multimedia server; multiple multidimensional subspace; quality of service; scalable multimedia disk scheduling; space-filling curve; Application software; Bandwidth; Computer networks; Intelligent networks; Laboratories; Processor scheduling; Quality of service; Scalability; Scheduling algorithm; Space technology;
fLanguage
English
Publisher
ieee
Conference_Titel
Data Engineering, 2004. Proceedings. 20th International Conference on
ISSN
1063-6382
Print_ISBN
0-7695-2065-0
Type
conf
DOI
10.1109/ICDE.2004.1320022
Filename
1320022
Link To Document