A Distributed Java Virtual Machine for a Beowulf Cluster |
|
|
|
This Project began as part of the ANU-Fujitsu
CAP Program, Phase III.
It is continuing over 2004--7 with funding of the ARC-funded Discovery
Project DP0449670,
Towards High-performance and Fault-tolerant Distributed
Java Implementations
.
This page is old dJVM project page, as at the start of 2004. The current dJVM Project Page is at http://djvm.anu.edu.au. ObjectivesJava is becoming increasingly important in implementing server applications. As many of these applications are multi-threaded with limited interaction between threads, a distributed JVM on a cluster platform may provide a cost-effective and high performance solution.The objective of this Project is to design, implement, and evaluate a distributed Jave Virtual Machine on a cluster computer. ApproachOur approach is to use the newly-released Jikes RVM as a basis for a distributed JVM. This is due to its use of advanced IT (Just-In-Time) translation for high performance. Its implementation, largely based on Java itself, makes it also suitable for such an extension.As an alternative to using a a general Distributed Shared Memory implementation, a more specialized scheme for distribution, which can better take advantage of Java's semantics, will be investigated. The target platform is the ANU Beowulf Cluster. This contemporary cluster has 96 dual Pentium III nodes connected using a Fast Ethernet switch; it is thus ideal to demonstrate scalability of a dJVM on a large, COTS cluster. The Research Team and ContactThe current dJVM team members are Steven Blackburn, Ramesh Sankaranarayana, James Sinnamon, Peter Strazdins, and John N Zigman. John is probably the most suitable for first contact about the Project.Project Milestones
Publications
Related Links
Peter Strazdins 2004-08-11 |
|
|
Validate Page |