Fault-tolerant scheduling for bag-of-tasks grid applications

Abstract

In this paper we propose a fault-tolerant scheduler for Bag-of-Tasks Grid applications, called WorkQueue with Replication Fault Tolerant (WQR-FT), obtained by adding checkpointing and replication to the WorkQueue with Replication (WQR) scheduling algorithm. By using discrete-event simulation, we show that WQR-FT not only ensures the successful completion of all the tasks in a bag, but also achieves performance better than WQR and other fault-tolerant schedulers obtained by coupling WQR with replication only, or with checkpointing only. © Springer-Verlag Berlin Heidelberg 2005.