Resource allocation in a distributed computing environment

Abstract

Advanced transportation systems can be expected to increasingly employ modern software development methodologies for the implementation of their operational capabilities. This is demanded by the shift to open architecture hardware and software solutions in order to meet stringent low-cost objectives. The common object request broker architecture (CORBA) is an important maturing standard offering interoperability among software components and portability across hardware platforms. While CORBA can provide needed interoperability and portability, the question arises how to manage distributed CORBA clients and servers in a fault tolerant manner. Future mission critical and distributed software deployments require effective resource allocation. Critical resource allocation issues that need to be addressed include component migration, scheduling, and load balancing across dynamic computational resources. A management system that addresses these issues in a uniform and cost-effective way is needed. This paper describes an integrated approach to optimal resource allocation and fault tolerance in a distributed computing environment. The approach leverages a commodity-off-the-shelf (COTS) resource allocation system to provide the infrastructure for the specific resource allocation and fault tolerance enhancements required to host a reliable CORBA applications on heterogeneous networked workstations.