Lock Removal for Concurrent Trace Programs

Abstract

Abstract. We propose a trace-based concurrent program analysis to soundly remove redundant synchronizations such as locks while preserving the behaviors of the concurrent computation. Our new method is computationally efficient in that it involves only thread-local computation and therefore avoids interleaving explosion, which is known as the main hurdle for scalable concurrency analysis. Our method builds on the partial-order theory and a unified analysis framework; therefore, it is more generally applicable than existing methods based on simple syntactic rules and ad hoc heuristics. We have implemented and evaluated the proposed method in the context of runtime verification of multithreaded Java and C programs. Our experimental results show that lock removal can significantly speed up symbolic predictive analysis for detecting concurrency bugs. Besides runtime verification, our new method will also be useful in applications such as debugging, performance optimization, program understanding, and maintenance.

Round-up: Runtime checking quasi linearizability of concurrent data structures

“…There also exists a large body of work on detecting violations of these properties (e.g. [21], [22], [23] and [24], [25], [26], [27], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43]). These bug finding methods differ from our new method in that they are checking for different types of properties.…”

Dynamic monitor allocation in the Java virtual machine

“…When removing lockwords of objects that are not used for locking the memory overhead could be further reduced. For this Kahlon and Wang proposed in [11] the removal of redundant synchronizations by only using thread-local computation. With this approach they were able to completely remove some lockwords while avoiding synchronization problems.…”