Run-Time Support for Dynamic Load Balancing and Debugging in Paralex

摘要

Paralex is a programming environment for developing and executing parallelapplications in distributed systems. The user is spared complexities of distributed programming including remote execution, data representation, communication, synchronization and fault tolerance as they are handled automatically by the system. Once an application starts execution in a distributed system it may be interacted with at two levels: by Paralex itself to achieve automatic fault tolerance and dynamic load balancing; or by the user in association with performance tuning and debugging. In this paper, we describe the set of monitors and control mechanisms that constitute the Paralex run-time system and their use for implementing dynamic load balancing and debugging.