The production of software systems with specific demand on reliability, availability, maintenance, and performance (RAMP) is one of the greatest challenges facing software engineers at all levels of the development cycle. Most requirements specification tools are more suited for functional requirements than for non-functional RAMP requirements. RAMP requirements are left unspecified, specified at a later stage, or at best vaguely specified, which makes requirements specifications more of an art than a science. Furthermore, the cost of testing for RAMP requirements is quite often prohibitive. In many cases, it is difficult to test for some of the RAMP specifications such as maintainability, reliability, and high availability. Even the test for performance is quite often workload dependent and as such the performance numbers provided at test time or at system commissioning time may not be achievable during actual system workload. What makes the subject matter more difficult is the absence of a clear set of rules or practices, which, if followed closely, produce a system with acceptable RAMP specifications. As such, and until the design of RAMP software systems becomes a well understood theme, the development of such systems will be a fine art, where the tools and capabilities of developing such systems will depend on the particular system to be developed, the environment in which it will run, and the level of expertise and knowledge deployed. Just like no two pieces of art produced by the same artist are the same, no two software systems will have the same RAMP characteristics. This paper will focus on the paradigms involved in the production of RAMP software systems through several case studies. The purpose is to promote the interest of researchers to develop more specific guidelines for the production of SW systems with well defined RAMP qualities.
