Workload characterization for trend analysis

ABSTRACT

The methodology of analysis proposed in this paper aims at predicting the workload of a computer. This methodology consists of applying an algorithm of clustering to the workload, its jobs being identified by a pair (X,P), where X is the resource-vector of the job and P stands for the priority given to the job by the user.The hereby obtained clusters are then associated to the a_i activities developed in the system and determine the influence of each a_i to the overall workload. By repeating this operation at different times, either the periodicity or the monotonic changes that may occur in each activity are determined. This makes it possible to predict the evolution of the overall workload and consequently to evaluate changes to be carried out in the system.The above methodology is applied to a specific case and is illustrated in its various phases. The results obtained have validated the method. The study is still going on, with continuous periodical observations in order to update the data.

REFERENCES

• 1: Ferrari, D., Workload Characterization and Selection in Computer Performance Measurement, Computer 4 (1972), 18--24
• 2: Ferrari, D., Computer Systems Performance Evaluation (Prentice-Hall, Englewood-Cliffs, 1978).
• 3: Agrawala, A. K., Mohr, J. M. and Bryant, R. M., An Approach to the Workload Characterization Problem, Computer 6 (1976), 18--29
• 4: Hellerman, H. and Conroy, T. F., Computer System Performance (McGraw-Hill, New York, 1975)
• 5: Artis, H. P., Capacity Planning for MVS Computer Systems in Ferrari, D., (ed.), Performance of Computer Installation (North Holland, Amsterdam, 1978) 25--53
• 6: Agrawala, A. K., Mohr, J. M., Predicting the Workload of a Computer System, Nat. Comp.Conf. (1978), 465--471
• 7: Anderberg, M. R., Cluster Analysis for Applications (Academic Press, New York, 1973)
• 8: Lebart, L., Morineau, A. and Tabard, N., Techniques de la description statistique (Dunod, Paris, 1977)
• 9: Forgy, E. W., Cluster Analysis of Multivariate Data: Efficiency versus Interpretability of Classification, Biometrics 21 (1965)
• 10: De Carlini, U., Mazzeo, A. and Savy, C., Analisi del carico di un sistema EDP per applicazioni didattiche e scientifiche, Congresso AICA, 1 (1979) Bari 295--303
• 11: Esposito, A., Mazzeo, A. and Savy, C., Systems Performance Evaluation: a Simulation Model for Batch Processing, in Dekker, L., Savastano, G. and Vansteenkiste, G. C. (eds.) Simulation of Systems 79 (North-Holland, Amsterdam, 1980)
• 12: Mc Rae, D. J., MIKCA: a FORTRAN IV Iterative K-means Cluster, CTB/McGraw-Hill (1970) Monterey
• 13: Ugo de Carlini , Antonio Mazzeo , Carlo Savy, Priority Batch Processing for Upper Bounded Response Times, Proceedings of the Third International Symposium on Modelling and Performance Evaluation of Computer Systems: Performance of Computer Systems, p.229-240, February 06-08, 1979
• 14: Lauro, N. and Costa, P., La caracterisation de la charge d'un systeme EDP par les methodes fa-torielles et la classification automatique, Analyse des Donnees, INRIA (1980) Napoli