An Ownership Policy and Deadlock Detector for Promises

TL;DR

This paper introduces an ownership-based approach and a lock-free runtime algorithm for deadlock detection in promise-based parallel programming, improving bug detection and reducing overheads.

Contribution

It proposes an ownership semantics for promises, a precise deadlock detection algorithm, and analyzes its correctness under modern memory models.

Findings

12% average time overhead in detection

6% average memory overhead

More efficient than previous deadlock detection methods

Abstract

Task-parallel programs often enjoy deadlock freedom under certain restrictions, such as the use of structured join operations, as in Cilk and X10, or the use of asynchronous task futures together with deadlock-avoiding policies such as Known Joins or Transitive Joins. However, the promise, a popular synchronization primitive for parallel tasks, does not enjoy deadlock-freedom guarantees. Promises can exhibit deadlock-like bugs; however, the concept of a deadlock is not currently well-defined for promises. To address these challenges, we propose an ownership semantics in which each promise is associated to the task which currently intends to fulfill it. Ownership immediately enables the identification of bugs in which a task fails to fulfill a promise for which it is responsible. Ownership further enables the discussion of deadlock cycles among tasks and promises and allows us to introduce a robust definition of deadlock-like bugs for promises. Cycle detection in this context is non-trivial because it is concurrent with changes in promise ownership. We provide a lock-free algorithm for precise runtime deadlock detection. We show how to obtain the memory consistency criteria required for the correctness of our algorithm under TSO and the Java and C++ memory models. An evaluation compares the execution time and memory usage overheads of our detection algorithm on benchmark programs relative to an unverified baseline. Our detector exhibits a 12% (1.12$\times$) geometric mean time overhead and a 6% (1.06$\times$) geometric mean memory overhead, which are smaller overheads than in past approaches to deadlock cycle detection.