Detection and Root Cause Analysis of Memory-Related Software Aging Defects by Automated Tests

Abstract

Memory-related software defects manifest after a long incubation time and are usually discovered in a production scenario. As a consequence, this frequently encountered class of so-called software aging problems incur severe follow-up costs, including performance and reliability degradation, need for workarounds (usually controlled restarts) and effort for localizing the causes. While many excellent tools for identifying memory leaks exist, they are inappropriate for automated leak detection or isolation as they require developer involvement or slow down execution considerably. In this work we propose a lightweight approach which allows for automated leak detection during the standardized unit or integration tests. The core idea is to compare at the byte-code level the memory allocation behavior of related development versions of the same software. We evaluate our approach by injecting memory leaks into the YARN component of the popular Hadoop framework and comparing the accuracy of detection and isolation in various scenarios. The results show that the approach can detect and isolate such defects with high precision, even if multiple leaks are injected at once.