Cloud-TM: Harnessing the Cloud with Distributed Transactional Memories.

P. Romano, N. Carvalho, L. Rodrigues, and J. Cachopo

Selected sections of this report will be published in the Proceedings of the 3rd ACM SIGOPS International Workshop on Large-Sacle Distributed Systems and Middleware (LADIS), Big Sky Resort, Big Sky (MT), USA, October 10-11, 2009.

Abstract

One of the main challenges to be addressed to harness the potential of Cloud computing lies in the design of programming models able to simplify the development of large scale parallel applications and allow ordinary programmers to take fully advantage of the computing power and storage provided by the Cloud, available on demand, in a pay-only-for-what-you-use pricing model.

In this paper we discuss the use of the Transactional Memory programming model in the context of the Cloud computing paradigm, which we refer to as Cloud-TM. We identify where existing Distributed Transactional Memory platforms still fail to meet the requirements of the cloud and of its users, and point several open research problems whose solution we deem as essential to materialize the Cloud-TM vision.

Also available extended report (pdf).