Content-aware resource scheduling for commercial and personal clouds

Organizations of all sizes are shifting their IT infrastructures to the cloud because of its cost efficiency and convenience. Because of the on-demand nature of Infrastructure as a Service (IaaS) clouds, hundreds of thousands of virtual machines (VMs) may be deployed and terminated in a single large cloud data center each day. At the same time, mobile devices are becoming the primary personal computing platform for hundreds of millions of consumers. Tablets and smart phones are becoming more and more common, and are replacing other forms of computation for most day-to-day tasks. In this thesis, we present solutions to lower costs of VM deployments in data centers. Also, we present cost-effective personal cloud storage service for mobile devices which uses similar techniques as in VM deployments in data centers. First, we present a content-based scheduling algorithm for the placement of VMs in data centers. We take advantage of the fact that it is possible to find identical disk blocks in different VM disk images with similar operating systems by scheduling VMs with high content similarity on the same hosts. That leads to significant savings in data center network utilization and congestion, by lowering the amount of data transfer associated with deployment of VMs. Second, we present a personal cloud storage service for mobile devices. Much as there is content similarity between VM disk images that share the same OSs, multiple devices that have the same owner tend to have similar content. We use that content similarity among an individual’s multiple mobile devices to minimize the network and storage costs of the personal cloud storage service