This Article 
 Bibliographic References 
 Add to: 
A Probabilistic Limit on the Virtual Size of Replicated Disk Systems
February 1992 (vol. 4 no. 1)
pp. 99-102

Recently, there has been considerable interest in parallel disk drive systems, in which full or partial replication of the stored data is used for both fault tolerance and enhanced performance. The performance-enhancement derives both from the ability to do parallel reads, and from the reduction of seek time which results from being able to assign a read to whichever drive will produce the shortest seek. Although earlier work implied that for a k-drive system, mean seek distance for read converges to 0 as k to alpha , a refined analysis is presented which shows that this limit is actually nonzero. It is further shown that the system behaves probabilistically as if k were small, no matter how large the physical value of k is.

[1] O. I. Aven, E. G. Coffman, Jr., and Y. A. Kogan,Stochastic Analysis of Computer Storage. Reidel, 1987.
[2] F. Baccelli and E. Coffman, "A database replication analysis using an M/M/m queue with service interruptions," inProc. 1982 ACM SIGMETRICS Conf. Measurement and Modeling of Comput. Syst., 1982, pp. 102-107.
[3] D. Bitton and J. Gray, "Disk shadowing," inProc. 14th Int. Conf. Very Large Databases, 1988, pp. 331-338.
[4] D. Bitton, "Arm scheduling in shadowed disks," inProc. Spring COMPCON 89, 1989, pp. 132-136.
[5] A. Calderbank, E. Coffman, and L. Flatto, "Sequencing problems in two-server systems,"Math. of Oper. Res., vol. 10, pp. 585-598, 1985.
[6] A. Hac', "Performance-reliability issues in distributed file systems,"J. Syst. and Software, vol. 6, pp. 219-224, 1986.
[7] M. Hofri, "Should the two-headed disk be greedy?,"Inform. Processing Lett., vol. 16, pp. 83-86, 1980.
[8] S. Karlin and H. Taylor,A First Course in Stochastic Processes. New York: Academic, 1975.
[9] N. Matloff,Probability Modeling and Computer Simulation, Applied to Engineering and Computer Science, Boston, MA: PWS-Kent, 1988.
[10] N. Matloff, "A multiple disk system for both fault tolerance and improved performance,"IEEE Trans. Reliability, vol. R-36, no. 2, pp. 199-201, 1987.
[11] N. Matloff and R. Lo, "A 'greedy' approach to the write problem in shadowed disk systems," inProc. Sixth Int. Conf. Data Eng., 1990, pp. 553-558.
[12] N. Matloff and A. Park, "Performance analysis of a random placement organization for shadowed disk systems," Tech. Rep., Division of Computer Science, Univ. of California at Davis, 1990.
[13] A. Park and K. Balasubramanian, "Providing fault tolerance in parallel secondary storage systems," Tech. Rep., Dep. Comput. Sci., Princeton Univ., 1986.
[14] D. A. Patterson, G. Gibson, and R. H. Katz, "A case for redundant arrays of inexpensive disks (RAID)," inProc. ACM SIGMOD, Chicago, IL, June 1-3, 1988, pp. 109-116.
[15] J. Stabile, "Disk scheduling algorithms for a multiple disk system," M.S. thesis, Univ. of California at Davis, 1987.
[16] K. S. Trivedi,Probability and Statistics with Reliability, Queueing and Computer Science Applications. Englewood Cliffs, NJ: Prentice-Hall, 1982.

Index Terms:
virtual size; replicated disk systems; parallel disk drive systems; fault tolerance; parallel reads; seek time; database theory; distributed databases; file organisation; magnetic disc storage
R.W.-M. Lo, N.S. Matloff, "A Probabilistic Limit on the Virtual Size of Replicated Disk Systems," IEEE Transactions on Knowledge and Data Engineering, vol. 4, no. 1, pp. 99-102, Feb. 1992, doi:10.1109/69.124901
Usage of this product signifies your acceptance of the Terms of Use.