The combination of independent and potentially heterogeneous parallel machines creates a powerful metacomputer. Such a metacomputer can be used to run a single parallel application if a single machine does not provide enough CPUs. However, achieving satisfactory application performance on such a metacomputer is difficult since instances of grid-related as well as non grid-related performance properties may introduce various wait states during communication and synchronization. In our earlier work, we have introduced an extension to the SCALASCA toolset for recording event traces of metacomputing applications and searching them automatically for patterns of inefficient behavior related to wide-area communication. Here, we show how this extension in combination with statistical analyses and time-line visualization provided by VAMPIR can be applied to evaluate and optimize the performance of a multi-physics production code running on a heterogeneous and geographically dispersed metacomputer.