Towards Defining Models of Hardware Capacity and Software Performance for Telecommunication Applications

Knowledge of the resource usage of applications and the resource usage capacity of hardware platforms is essential when developing a system. The resource usage must not over exceed the capacity of a platform, as it could otherwise fail to meet its real-time constraints due to resource shortages. Furthermore, it is beneficial from a cost-effectiveness stand-point that a hardware platform is not under-utilised by systems software. This thesis examines two systems aspects: the hardware resource usage of applications and the resource capacity of hardware platforms, defined as the capacity of each resource included in a hardware platform. Both of these systems aspects are investigated and modelled using a black box perspective since the focus is on observing the online usage and capacity. Investigating and modelling these two approaches is a crucial step towards defining and constructing hardware and software models. We evaluate regressive and auto-regressive modelling approaches of modelling CPU, L2 cache and L3 cache usage of applications. The conclusion is that first-order autoregressive and Multivariate Adaptive Regression Splines show promise of being able to model resource usage. The primary limitation of both modelling approaches is their inability to model resource usage when it is highly irregular. The capacity models of CPU, L2 and L3 cache derived by exerting heavy workloads onto a test platform shows to hold against a real-life application concerning L2 and L3 cache capacity. However, the CPU usage model underestimates the test platform's capacity since the real-life application over-exceeds the theoretical maximum usage defined by the model