Enhancing concurrency in distributed transactional memory through commutativity

Abstract

Distributed software transactional memory is an emerging, alternative concurrency control model for distributed systems promising to alleviate the difficulties of lock-based distributed synchronization. We consider the multi-versioning (MV) model to avoid unnecessary aborts. MV schemes inherently guarantee commits of read-only transactions, but limit the concurrency of write transactions. In this paper we propose CRF (Commutative Requests First), a new scheduler tailored for enhancing concurrency of write transactions. CRF relies on the notion of commutative transactions, namely conflicting transactions that leave the state of the shared data-set consistent even if validated and committed concurrently. CRF is responsible to detect conflicts among commutative and non-commutative write transactions and then schedules them according to the execution state. We assess the goodness of the approach by an extensive evaluation of a fully implementation of CRF. The tests reveal that CRF improves throughput over a state-of-the-art DTM solution. © 2013 Springer-Verlag.