I/O Performance Isolation Analysis and Optimization on Linux Containers

Container enables a new way to run applications by containerizing the application, which provides kinds of services to make them portable, extensible, and easy to be transferred between private data centers and public clouds. Comparing with virtual machines, containers have several advantages in terms of simplicity, low-overhead and lightweight. However, as the OS kernel and resources are shared by all the hosted containers, performance isolation becomes a challenging issue for guaranteeing their SLA. This paper discusses I/O performance isolation issue in container-based clusters. First, we analyze the characteristics of I/O performance isolation from the perspective of the SLA. Then we conduct the observation experiments using multiple containers to obtain the variation trend of the I/O performance parameters and observe the impact of the I/O overload container on the I/O performance isolation of the system. Finally, we propose two algorithms, SLAE and UTE, to improve the I/O performance isolation in container-based systems. These algorithms contribute to decrease the interference caused by the overloaded containers. Experimental results show the feasibility and effectiveness of our proposed algorithms. Keywords-Container-based System; I/O Performance Isolation; SLA; Docker;