A Virtual CPU Scheduling Model for I/O Performance in Paravirtualized Environments

Abstract

Paravirtualization manages virtual machines and virtual resources efficiently by the communication between the virtualization layer and modified guest OSes. In a paravirtual environment, the I/O response of a virtual machine is hard to approach that of a native OS because a virtual I/O is asynchronously processed by the virtualization layer without hardware supports. Virtual CPU scheduling algorithms have been proposed to improve the I/O performance. However, existing solutions lack the I/O fairness when virtual machines have various or skewed of workloads because they put the I/O performance of latency-sensitive vCPUs before vCPUs that are not. In this paper, we design a credit based vCPU scheduling model for I/O performance of virtual machines by using a loan and repayment system. Credit rating of each virtual CPU is periodically evaluated by observing its resource consumption pattern and a virtual CPU cannot be allocated more resources until the repayment is finished.