SUMMARYJavelin is a Java-based infrastructure for global computing. This paper presents Javelin++, an extension of Javelin, intended to support a much larger set of computational hosts. Contributions to scalability and fault tolerance are presented. This is the focus of the paper. Two scheduling schemes are presented: probabilistic work stealing and deterministic work stealing. The distributed deterministic work stealing is integrated with a distributed deterministic eager scheduler, which is one of the paper's primary original contributions. An additional fault tolerance mechanism is implemented for replacing hosts that have failed or retreated. A Javelin++ API is sketched, then illustrated on a raytracing application. Performance results for the two schedulers are reported, indicating that Javelin++, with its broker network, scales better than the original Javelin.

Javelin is a Java-based infrastructure for global computing. This paper presents Javelin++, an extension of Javelin, intended to support a much larger set of computational hosts. First, Javelin++'s switch from Java applets to Java applications is explained. Then, two scheduling schemes are presented: a probabilistic work-stealing scheduler and a deterministic scheduler. The deterministic scheduler also implements eager scheduling, as well as another fault-tolerance mechanism for hosts that have failed or retreated. A Jav-elin++ API is sketched, then illustrated on a raytracing application.Performance results for the two schedulers are reported, indicating that Javelin++, with its broker network, scales better than the original Javelin.. No direct point-to-point communicntn'on -since applets may not accept any connections, and may only initiate connections back to the server from where they were downloaded, point-to-point communication can be achieved only by providing special routing servers that relay all messages sent by Javelin hosts. This is a serious performance drawback, and the task of implementing the network routing service is tedious, especially with respect to fault tolerance.

No abstract