Distributed Virtual Diskless Checkpointing: A Highly Fault Tolerant Scheme for Virtualized Clusters

Today's high-end computing systems are facing a crisis of high failure rates due to increased numbers of components. Recent studies have shown that traditional fault tolerant techniques incur overheads that more than double execution times on these highly parallel machines. Thus, future high-end computing must be able to provide adequate fault tolerance at an acceptable cost or the burdens of fault management will severely affect the viability of such systems. Cluster virtualization offers a potentially unique solution for fault management, but brings significant overhead, especially for I/O. In this paper, we propose a novel diskless check pointing technique on clusters of virtual machines. Our technique splits Virtual Machines into sets of orthogonal RAID systems and distributes parity evenly across the cluster, similar to a RAID-5 configuration, but using VM images as data elements. Our theoretical analysis shows that our technique significantly reduces the overhead associated with check pointing by removing the disk I/O bottleneck.