Cooperative Cache For Virtual Machine’s Images In Cloud Computing Environment

Recent years, the cloud computing has run into an explosive development in ashort time, cloud computing is a main stream of IT industry’s development now. In thepractical run of cloud computing, the service providers frequently run up against thelarge-scale virtual environment, and have to content the needs of large-scale virtualmachine clusters. Because virtualization technology and distribute storage technologyare the key support technologies of cloud computing, to speed up the deployment ofvirtual machine clusters is a shortcut of improving system’s performance and enhancingusers’ experience. To meet the goal of speed up the deployment of virtual machineclusters, some cloud computing systems adopt distribute storage and fast cachetechnology. But cache can only serve for the virtual machines locate in the samephysical machine, it cannot improve the system’s data serve ability in general.By analyzing the problems and challenges of virtual machine image store system incloud computing environment, we present a cooperative cache (CoCache) for virtualmachines’ image data. CoCache takes advantage of the service ability of the cachednodes by providing virtual image data service for other nodes. CoCache can transferdata between nodes in a P2P pattern, for extending data service ability of the system.CoCache is realized in the kernel space of Linux, can support any kind of VMM.Experiments show that CoCache can effectively reduce the cost during virtual machinesread data, and promote the service ability of virtual machine storage system.This paper presents a new cache replacement policy which based on dataimportance measure algorithm to address the problem that traditional cache replacementpolicy. The data importance measure algorithm evaluate a data block’s importanceaccording to the frequency and the scope it’s read. Then simulative experiments proveits effectiveness subsequently.