IOFollow: Improving the performance of VM live storage migration with IO following in the cloud

Abstract

VM live migration becomes critical to deployment in the Cloud, as to enable fast and transparent workload rescheduling among unevenly utilized physical nodes, aimed at high performance and energy efficient utilization of computer server resources. Nevertheless, VM I/O intensity can significantly impact the performance of VM live storage migration due to contention for the shared disk bandwidth and system resources. Based on this observation, this paper proposes the IOFollow scheme to improve simultaneously the VM performance and migration performance. IOFollow mitigates the I/O interference between VM I/O requests and migration I/O requests, by scheduling the migration sequence according to the access pattern of VM I/O requests. In addition, it improves the cache management efficiency by exploiting the semantic information from the VMs and migration threads. Results obtained from trace-based experiments on a lightweight prototype implementation of IOFollow indicate that IOFollow system is highly competitive, improving both the VM performance and migration performance significantly when compared to existing design.