备份
快照(计算机存储)
计算机科学
操作系统
覆盖
虚拟机
并行计算
作者
Tinnaphob Angkaprasert,Kasidit Chanchio
标识
DOI:10.1109/jcsse58229.2023.10202119
摘要
This paper investigates the use of ZFS filesystem to improve the checkpointing mechanisms and the backup of the disk image of QEMU-KVM. In the traditional method, QEMU-KVM has to create a new QCOW2 overlay disk image file at every checkpoint operation. After checkpointing many times, the number of overlay disk images can be overwhelming. These overlay disk images have a dependency on one another. Therefore, the traditional method requires high maintenance costs and takes a long time to restore a VM from a checkpoint. In this paper, we introduce a Snapshot Manager to create a checkpoint of a VM, manage ZFS snapshots, and back up the snapshot from one host to another. By using ZFS filesystem, the Snapshot Manager reduces the number of disk images to one. This approach makes it much easier and causes very low overheads to manage VM checkpoints and disk images. In terms of performance, our experimental results show that ZFS takes significantly less restoration time of a VM than the traditional method at the cost of moderately higher backup time.
科研通智能强力驱动
Strongly Powered by AbleSci AI