Improving I/O Resource Sharing of Linux Cgroup for NVMe SSDs on Multi-core Systems

In container-based virtualization where multiple isolat-ed containers share I/O resources on top of a single operating system, efficient and proportional I/O re-source sharing is an important system requirement. Mo-tivated by a lack of adequate support for I/O resource sharing in Linux Cgroup for high-performance NVMe SSDs, we developed a new weight-based dynamic throttling technique which can provide proportional I/O sharing for container-based virtualization solutions run-ning on NUMA multi-core systems with NVMe SSDs. By intelligently predicting the future I/O bandwidth requirement of containers based on past I/O service rates of I/O-active containers, and modifying the cur-rent Linux Cgroup implementation for better NUMA-scalable performance, our scheme achieves highly ac-curate I/O resource sharing while reducing wasted I/O bandwidth. Based on a Linux kernel 4.0.4 implementa-tion running on a 4-node NUMA multi-core systems with NVMe SSDs, our experimental results show that the proposed technique can efficiently share the I/O bandwidth of NVMe SSDs among multiple containers according to given I/O weights.