VMckpt:lightweight and live virtual machine checkpointing  

作　　者：LIU HaiKun JIN Hai LIAO XiaoFei MA Bo XU ChengZhong 

机构地区：[1]Services Computing Technology and System Lab, Cluster and Grid Computing Lab,School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China [2]Department of Electrical and Computer Engineering, Wayne State University, Detroit, MI 48202, USA

出　　处：《Science China(Information Sciences)》2012年第12期2865-2880,共16页中国科学（信息科学）（英文版）

基　　金：supported by National Basic Research Program of China(Grant No.2007CB310900);China National Natural Science Foundation(NSFC)(Grant Nos.60973133,61133006);MoE-Intel Information Technology Special Research Foundation(Grant No.MOE-INTEL-10-05);U.S.NSF(Grant No.CNS-0914330)

摘　　要：Recent advance of virtualization technology provides a new approach to check-point/restart at the virtual machine （VM） level. In contrast to traditional process-level checkpointing, checkpointing at the vir- tualization layer brings up several advantages, such as compatibility, transparence, flexibility and simplicity. ttowever~ because the virtualization layer has little semantic knowledge about the operation system and the applications running atop, VM-layer checkpointing requires saving the entire operating system state rather than a single process. The overhead may render the approach impractical. To reduce the size of VM checkpoint, in this paper we propose a page eviction scheme and an incremental checkpointing mechanism to avoid saving un- necessary VM pages in the checkpoint. To keep the system online transparently, we propose a live checkpointing mechanism by saving the memory image in a copy-on-write （COW） manner. We implement the performance optimization mechanisms in a prototype system, called VMckpt. Experimental results with a group of represen- tative applications show that our page eviction scheme and incremental checkpointing can significantly reduce the checkpoint file size by up to 87% and shorten the total checkpointing/restart time by a factor of up to 71%, in comparison with the Xens default cheekpointing mechanism. The observed application downtimes due to eheckpointing can be reduced to as small as 300 ms.Recent advance of virtualization technology provides a new approach to check-point/restart at the virtual machine （VM） level. In contrast to traditional process-level checkpointing, checkpointing at the vir- tualization layer brings up several advantages, such as compatibility, transparence, flexibility and simplicity. ttowever~ because the virtualization layer has little semantic knowledge about the operation system and the applications running atop, VM-layer checkpointing requires saving the entire operating system state rather than a single process. The overhead may render the approach impractical. To reduce the size of VM checkpoint, in this paper we propose a page eviction scheme and an incremental checkpointing mechanism to avoid saving un- necessary VM pages in the checkpoint. To keep the system online transparently, we propose a live checkpointing mechanism by saving the memory image in a copy-on-write （COW） manner. We implement the performance optimization mechanisms in a prototype system, called VMckpt. Experimental results with a group of represen- tative applications show that our page eviction scheme and incremental checkpointing can significantly reduce the checkpoint file size by up to 87% and shorten the total checkpointing/restart time by a factor of up to 71%, in comparison with the Xens default cheekpointing mechanism. The observed application downtimes due to eheckpointing can be reduced to as small as 300 ms.

关 键 词：checkpoint/restart copy-on-write page eviction virtual machine 

分 类 号：TP311.131[自动化与计算机技术—计算机软件与理论] TP316[自动化与计算机技术—计算机科学与技术]