Predicting Performance by Analytically Solving a Queueing Network Model

摘要

An approach is provided for predicting system performance. The approach operates by identifying a Queuing Network Model (QNM) corresponding to an information technology (IT) environment that includes a number of servers that perform a plurality of parallel services. The QNM is transformed to a linear model by serializing the parallel services as sequential services. Hardware based service demands are retrieved from the system. Software-based service demands are inferred from the hardware-based service demands. Predicted performance results of the IT environment are calculated based on the hardware-based service demands, the software-based service demands inferred from the hardware-based service demands, and the system transaction rate of the system.

主权项

1. A method, in an information handling system comprising one or more processors and a memory, of predicting system performance, the method comprising:
identifying a Queuing Network Model (QNM) corresponding to an information technology (IT) environment that includes a plurality of servers and that perform a plurality of parallel services; transforming the QNM to a linear model by serializing the parallel services as sequential services; retrieving a plurality of hardware-based service demands; inferring a plurality of software-based service demands based on the plurality of hardware-based service demands; receiving a system transaction rate based on a user test of the IT environment; and calculating one or more predicted performance results of the IT environment based on the plurality of hardware-based service demands, the plurality of software-based service demands, and the system transaction rate.