Abstract
Non-functional properties such as memory footprint have recently gained importance in software product line research. However, determining the memory characteristics of individual features and product variants is extremely challenging. We present an approach that supports the monitoring of memory characteristics of individual features at the level of Java virtual machines. Our approach provides extensions to Java virtual machines to track memory allocations and deal-locations of individual features based on a feature-to-code mapping. The approach enables continuous monitoring at the level of features to detect anomalies such as memory leaks, excessive memory consumption, or abnormal garbage collection times in product variants. We provide an evaluation of our approach based on different product variants of the DesktopSearcher product line. Our experiment with different program inputs demonstrates the feasibility of our technique.
Users
Please
log in to take part in the discussion (add own reviews or comments).