Controlled Concurrency Testing via Periodical Scheduling

Abstract

Controlled concurrency testing (CCT) techniques have been shown promising for concurrency bug detection. Their key insight is to control the order in which threads get executed, and attempt to explore the space of possible interleavings of a concurrent program to detect bugs. However, various challenges remain in current CCT techniques, rendering them ineffective and ad-hoc. In this paper, we propose a novel CCT technique Period. Unlike previous works, Period models the execution of concurrent programs as periodical execution, and systematically explores the space of possible inter-leavings, where the exploration is guided by periodical scheduling and influenced by previously tested interleavings. We have evaluated Period on 10 real-world CVEs and 36 widely-used benchmark programs, and our experimental results show that Period demonstrates superiority over other CCT techniques in both effectiveness and runtime overhead. Moreover, we have discovered 5 previously unknown concurrency bugs in real-world programs.