Location-Aware Cache-Coherence Protocols for Distributed Transactional Contention Management in Metric-Space Networks

Transactional Memory API utilizes contention managers to guarantee that whenever two transactions have a conflict on a resource, one of them is aborted. Compared with multi-processor transactional memory systems, the design of dis-tributed transactional memory systems is more challenging because of the need for distributed cache-coherence proto-cols and the underlying (higher) network latencies involved. The choice of the combination of the contention manager and the cache-coherence protocol is critical for the perfor-mance of distributed transactional memory systems. We show that the performance of a distributed transactional memory system on metric-space networks is O(N2i) for Ni transactions requesting for a single object under the Greedy contention manager and an arbitrary cache-coherence pro-tocol. To improve the performance, we propose a class of location-aware distributed cache-coherence protocols, called LAC protocols. We show that the combination of the Greedy contention manager and an efficient LAC proto-col yields an O(N logN · s) competitive ratio, where N is the maximum number of nodes that request the same object, and s is the number of objects. This is the first such per-formance bound established for distributed transactional memory contention managers. Our results yield the follow-ing design strategy: select a distributed contention man-ager and determine its performance without considering distributed cache-coherence protocols; then find an appro-priate cache-coherence protocol to improve performance. 1