Stable deterministic multithreading through schedule memoization

Abstract

A deterministic multithreading (DMT) system eliminates nondeterminism in thread scheduling, simplifying the development of multithreaded programs. However, existing DMT systems are unstable; they may force a program to (ad)venture into vastly different schedules even for slightly different inputs or execution environments, defeating many benefits of determinism. Moreover, few existing DMT systems work with server programs whose inputs arrive continuously and nondeterministically.TERN is a stable DMT system. The key novelty in TERN is the idea of schedule memoization that memoizes past working schedules and reuses them on future inputs, making program behaviors stable across different inputs. A second novelty in TERN is the idea of windowing that extends schedule memoization to server programs by splitting continuous request streams into windows of requests. Our TERN implementation runs on Linux. It operates as user-space schedulers, requiring no changes to the OS and only a few lines of changes to the application programs. We evaluated TERN on a diverse set of 14 programs (e.g., Apache and MySQL) with real and synthetic workloads. Our results show that TERN is easy to use, makes programs more deterministic and stable, and has reasonable overhead.