The increased use of virtual machines in the enterprise environment presents an interesting new set of challenges for the administrators of today's information systems. In addition to the management of the sheer volume of easily-created new data on physical machines, VMs themselves contain data that is important to the user of the virtual machine. Efficient storage, transmission, and backup of VM images has become a growing concern. We present IZO, a novel large-window compression tool inspired by data deduplication algorithms, which provides significantly faster and better compression than existing large-window compression tools. We apply this tool to a number of VM management domains, including deep-freeze, backup, and transmission, to more efficiently store, administer, and move virtual machines.
Mark A. Smith, Jan Pieper, Daniel Gruhl, Lucas Vil