DocumentCode
3456060
Title
Improving parallelism in I/O systems
Author
Lee, Keok-Kee ; Varman, P.
Author_Institution
Sch. of Appl. Sci., Nanyang Technol. Univ., Singapore
fYear
1995
fDate
3-7 Jul 1995
Firstpage
210
Lastpage
214
Abstract
The problem of improving the performance of external merging in a parallel I/O system using read-ahead prefetching and disk scheduling is studied. A Markov model is developed and numerically solved for a two-disk two-run system. Larger configurations are studied using simulation. A scheduling algorithm to maximize I/O parallelism is also presented
Keywords
Markov processes; input-output programs; merging; parallel processing; scheduling; storage management; I/O systems; Markov model; disk scheduling; external merging; parallelism; performance; read-ahead prefetching; scheduling algorithm; two-disk two-run system; Analytical models; Bismuth; Computational modeling; Concurrent computing; Merging; Parallel processing; Performance analysis; Prefetching; Processor scheduling; Scheduling algorithm;
fLanguage
English
Publisher
ieee
Conference_Titel
Networks, 1995. Theme: Electrotechnology 2000: Communications and Networks. [in conjunction with the] International Conference on Information Engineering., Proceedings of IEEE Singapore International
Print_ISBN
0-7803-2579-6
Type
conf
DOI
10.1109/SICON.1995.526048
Filename
526048
Link To Document