Abstract:
Hit ratio is the primary measure of disk cache buffer efficiency, and may be contrasted against cache overhead. A technique to calculate the lower bound of hit ratio base...Show MoreMetadata
Abstract:
Hit ratio is the primary measure of disk cache buffer efficiency, and may be contrasted against cache overhead. A technique to calculate the lower bound of hit ratio based on cache overhead is presented. A method to calculate average hit ratio based on I/O tracing is also developed. Finally, an example is cited showing that a hit ratio as low as 14% will offer a performance improvement over similar disk drives equipped with noncaching buffers.<>
Published in: Digest of Papers COMPCON Spring 1992
Date of Conference: 24-28 February 1992
Date Added to IEEE Xplore: 06 August 2002
Print ISBN:0-8186-2655-0
References is not available for this document.
Select All
1.
M. J. Bach, Design of the Unix Operating System, Prentice-Hall, 1986.
2.
M. H. Degroot, Probability and Statistics, Addison-Wesler, 1986.
3.
H. Hellerman, Computer System Performance, McGraw-Hill, 1975.
4.
Method for Analyzing Performance of Computer Peripherals, July 1989.
5.
W. C. Lynch, "Do Disk Arms Move?", Performance Evaluation Review, vol. 1, Dec 1972.
6.
D. J. Makaroff, Disk Cache Performance of Distributed Systems, Dept of Comp. Sci., Univ. of Saskatchewan, 1990.
7.
J. Menon, The IBM Model 3 Disk Cache, Dec 1987.
8.
A. J. Smith, "Disk Cache Miss Ratio Analysis and Considerations", ACM Trans on Computer Sys, vol. 3, no. 3, Aug 1985.
9.
J. Zahorjan, "A Queuing Model of a Rotational Position Sensing Disk", Infor, vol. 16, no. 2, Oct 1978.
