The complexity of computer systems requires to con- sider the interaction of several workloads. Only a limited number of business and technical workloads are usually re- quired to properly model the system. In this paper, we discuss regression-based estimates of service times required for model parametrization and we focus on the selection of significant workloads. We present an experimental comparison, using real perfor- mance logs of a distributed enterprise application, illus- trating the benefits of constrained estimations over the tra- ditional approach based on ordinary linear regression.
How to select significant workloads in performance models
Casale, Giuliano;Cremonesi, Paolo;Turrin, Roberto
2007-01-01
Abstract
The complexity of computer systems requires to con- sider the interaction of several workloads. Only a limited number of business and technical workloads are usually re- quired to properly model the system. In this paper, we discuss regression-based estimates of service times required for model parametrization and we focus on the selection of significant workloads. We present an experimental comparison, using real perfor- mance logs of a distributed enterprise application, illus- trating the benefits of constrained estimations over the tra- ditional approach based on ordinary linear regression.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
