Understanding the dependency between performance metrics (such as response time) and software configuration or usage parameters is crucial in improving software quality. However, the size of most modern systems makes it nearly impossible to provide a complete performance model. Hence, we focus on scenario-specific problems where software engineers require practical and efficient approaches to draw conclusions, and we propose an automated, measurement-based model inference method to derive goal-oriented performance prediction functions. For the practicability of the approach it is essential to derive functional dependencies with the least possible amount of data. In this paper, we present different strategies for automated improvement of the prediction model through an adaptive selection of new measurement points based on the accuracy of the prediction model. In order to derive the prediction models, we apply and compare different statistical methods. Finally, we evaluate the different combinations based on case studies using SAP and SPEC benchmarks.
Abstract-Evaluating the performance (timing behavior, throughput, and resource utilization) of a software system becomes more and more challenging as today's enterprise applications are built on a large basis of existing software (e.g. middleware, legacy applications, and third party services). As the performance of a system is affected by multiple factors on each layer of the system, performance analysts require detailed knowledge about the system under test and have to deal with a huge number of tools for benchmarking, monitoring, and analyzing. In practice, performance analysts try to handle the complexity by focusing on certain aspects, tools, or technologies. However, these isolated solutions are inefficient due to the small reuse and knowledge sharing. The Performance Cockpit presented in this paper is a framework that encapsulates knowledge about performance engineering, the system under test, and analyses in a single application by providing a flexible, plug-in based architecture. We demonstrate the value of the framework by means of two different case studies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.