期刊名称：International Journal of Distributed Sensor Networks
印刷版ISSN：1550-1329
电子版ISSN：1550-1477
出版年度：2013
卷号：2013
DOI：10.1155/2013/625070
出版社：Hindawi Publishing Corporation
摘要：In distributed wireless sensor networks (DWSNs), the data gathered by sink is always massive and consumes a lot of resources. It is suitable for cloud computing platform to apply service in data processing system. In cloud computing, IAAS platform provides services and calculation to the user through the virtual machine. The management of virtual machine images not only consumes a huge amount of storage space but also gives large pressure on network transmission. By using deduplication technology in openstack, this paper designed and implemented, an image management system IM-dedup, which uses static chunking (SC) to divide image file into blocks of data, avoid duplication data blocks transmission on network by using fingerprint pretransmission technology, and reduce storage space by deploying kernel mode file system with deduplication in the image storage server. The experimental results showed that the system not only reduced 80% usage of the virtual machine image storage, but also saved at least 30% of transmission time. Furthermore, the research on virtual machine image format showed that “VMWare Virtual Machine Disk Format” (VMDK), “Virtual Desktop Infrastructure” (VDI), “QEMU Copy On Write2” (QCOW2), and RAW image formats are more suitable for the IM-dedup system.
