Detecting software aging in a cloud computing framework by comparing development versions

Software aging, i.e. degradation of software performance or functionality caused by resource depletion is usually discovered only in the production scenario. This incurs large costs and delays of defect removal and requires provisional solutions such as rejuvenation (controlled restarts). We propose a method for detecting aging problems shortly after their introduction by runtime comparisons of different development versions of the same software. Possible aging issues are discovered by analyzing the differences in runtime traces of selected metrics. The required comparisons are workload-independent which minimizes the additional effort of dedicated stress tests. Consequently, the method requires only minimal changes to the traditional development and testing process. This paves the way to detecting such problems before public releases, greatly reducing the cost of defect fixing. Our study focuses on the memory leaks of Eucalyptus, a popular open source framework for managing cloud computing environments.