Abstract
The performance of a disk system is often measured in terms of the length of the waiting line or queue of requests for each of the system's spindles. Thus it is natural to formulate and analyze queueing models of disk systems. While most disk systems have certain characteristics, such as channel interference and concurrent seeks, in common, previous analyses have always been begun from scratch, without exploiting this commonality. We introduce a general queueing model for disk systems, which incorporates the characteristics common to most disk systems, and use it in the approximate analyses of models of the IBM 2314 and 3330 disk systems. Comparisons with simulation statistics show that the approximations made are very good over a wide range of arrival rates and system parameters. We also show how to use the analytic results to investigate performance differences between devices.
- 1 ABATE, J , DUBNER, H , AND WEINBERG. S Queuemg analysis of the IBM 2314 disk storage facility J ACM 15, 4 (Oct 1968), 577-589 Google Scholar
- 2 BARD, Y Task queuing m auxdmry storage devices with rotational position sensing Rep G320-2070, IBM Cambridge Scl Ctr, Cambridge, Mass , March 1971Google Scholar
- 3 CONWAV, R W , MAXWELL. W L , AND MILLER, L W Theory of Scheduhng Addison-Wesley, Reading, Mass , 1967Google Scholar
- 4 Cox, D R , AND SMIT8, W L Queues Chapman and Hall, London, 1961Google Scholar
- 5 CRANE, M A, ANO IOLEHART, D.L. Slmulatmg stable stochastic systems, I. General multtserver queues J ACM21, 1 (Jan 1974), 103-113 Google Scholar
- 6 GOTLIEB, C C, AND MACEWEtq, G H Performance of moveable-head disk storage devices J. ACM 20, 4 (Oct 1973), 604-623 Google Scholar
- 7 HENRICI, P Elements of Numerical Analysts Wdey, New York, 1964Google Scholar
- 8 KR~TZtNGER. P S. An approach to the opumtzatton of d~rect access merge performance. Res. Rep. CSRR 2066, Dep Apphed Analys~s and Comptr Scl, U of Waterloo, Waterloo, Ont, Canada, 1972Google Scholar
- 9 LITrLE, J D C A proof of the queuing formula. L = hW Oper Res 9 (1961), 383-387Google Scholar
- 10 MANOCnA, T Analysis of an input/output subsystem w~th seek-type direct-access dewces IEEE Comptr Conf, 1972, pp 155-158Google Scholar
- 11 SKINNER, C.F. A priority queuing system with server walking time Oper. Res. 15 (1967), 278-285.Google Scholar
- 12 TAKACS, L On a stochastic process concernmg some wamng t~me problems Theory Probabzhty and Its Appl II (1957), 90-102Google Scholar
- 13 TEO~EY, T J The role of d~sk scheduhng m multlprogrammed computer systems Ph.D Th , U of W~sconsm, Madison, Wls, 1972Google Scholar
Index Terms
- A General Model for the Performance of Disk Systems
Recommendations
Performance of Two-Disk Failure-Tolerant Disk Arrays
RAID5 disk arrays use the rebuild process to reconstruct the contents of a failed disk on a spare disk, but this process is unsuccessful if latent sector failures are encountered or a second disk failure occurs. The high cost of data loss has led to two-...
DCD—disk caching disk: a new approach for boosting I/O performance
ISCA '96: Proceedings of the 23rd annual international symposium on Computer architectureThis paper presents a novel disk storage architecture called DCD, Disk Caching Disk, for the purpose of optimizing I/O performance. The main idea of the DCD is to use a small log disk, referred to as cache-disk, as a secondary disk cache to optimize ...
Comments