Tiago Vale (2012)

MSc Student

in

MSc dissertation: A Modular Distributed Transactional Memory Framework  
Period: Jan 2011 — Sep 2012
Grade: 20/20 points (the highest grade possible)
Project: Synergy-VM project (funded by the National Science Foundation, PI: Prof. João Lourenço)
Papers: Euro-Par'12 (DOI) [distinguished paper award], INForum 2012

Abstract:

The traditional lock-based concurrency control is complex and error-prone due to its low-level nature and composability challenges. Software transactional memory (STM), inherited from the database world, has risen as an exciting alternative, sparing the programmer from dealing explicitly with such low-level mechanisms. In real world scenarios, software is often faced with requirements such as high availability and scalability, and the solution usually consists on building a distributed system. Given the benefits of STM over traditional concurrency controls, Distributed Software Transactional Memory (DSTM) is now being investigated as an attractive alternative for distributed concurrency control. Our long-term objective is to transparently enable multithreaded applications to execute over a DSTM setting. In this work we intend to pave the way by defining a modular DSTM framework for the Java programming language. We extend an existing, efficient, STM framework with a new software layer to create a DSTM framework. This new layer interacts with the local STM using well-defined interfaces, and allows the implementation of different distributed memory models while providing a non-intrusive, familiar, programming model to applications, unlike any other DSTM framework. Using the proposed DSTM framework we have successfully, and easily, implemented a replicated STM which uses a Certification protocol to commit transactions. An evaluation using common STM benchmarks showcases the efficiency of the replicated STM, and its modularity enables us to provide insight on the relevance of different implementations of the Group Communication System required by the Certification scheme, with respect to performance under different workloads.

Keywords: Transactional Memory, Distributed Systems, Concurrency Control, Replication