Abstract

In recent years a number of load sharing (LS) mechanisms have been proposed or implemented to fully utilize system resources. We have designed and implemented a decentralized real-time LS mechanism based on the Condor package [17, 18]. Two important features of our design are use of region-change broadcasts in the information policy to provide each workstation with timely state information at minimum communication cost, and use of preferred lists in the location policy to avoid task collisions. With these two features, we remove the central manager workstation in Condor, configure its functionalities into each participating workstation, transform Condor into a decentralized LS mechanism, and equip Condor with the capability to tolerate single workstation failures. Also discussed are the experiments on the proposed LS mechanism and the off-the-shelf Condor package and our observations of empirical data. Index Terms : distributed systems, adaptive load sharing, region-change broadcasts, ...

Citations