Cloud customers can scale the resources according to their needs in order to avoid application bottleneck. The scaling can be done in two ways, either by increasing the existing virtual machine instance with additional resources, or by adding an additional virtual machine instance with the same resources. Although it is expected that the costs rise proportionally to scaling, we are interested in finding out which organization offers scaling with better performance. The goal of this paper is to determine the resource organization that produces better performance for the same cost, and help the customers decide if it is better to host a web application on a more ”small” instances or less ”large” instances. The first hypothesis states that better performance is obtained by using more and smaller instances. The second hypothesis is that the obtained speedup while scaling the resources is smaller than the scaling factor. The results from the provided experiments have not proven any of the hypotheses, meaning that using less, but larger instances results with better performance and that the user gets more performances than expected by scaling the resources.