DTHREADS: Efficient and Deterministic Multithreading

Multithreaded programming is notoriously difficult to get right. A key problem is non-determinism, which complicates debugging, testing, and reproducing errors in multithreaded applications. One way to simplify multithreaded programming is to enforce deterministic execution. However, past deterministic systems are incomplete or impractical. Language-based approaches require programmers to write their code in specialized languages. Other systems require program modification, do not ensure determinism in the presence of data races, do not work with general-purpose multithreaded programs, or suffer substantial performance penalties (up to 8× slower than pthreads) that limit their usefulness. This paper presents DTHREADS, an efficient deterministic multithreading system for unmodified C/C++ applications. DTHREADS not only prevents semantic errors like race conditions and deadlocks, but also can enhance performance by eliminating false sharing of cache lines. DTHREADS leverages virtual memory and process isolation, combined with a deterministic commit protocol, to ensure robust deterministic execution with low runtime overhead. Experimental results show that DTHREADS substantially outperforms a state-of-the-art deterministic runtime system, and often matches—and occasionally exceeds—the performance of pthreads.