Resource Virtualization for Cluster-Based Network Storage Service
Resource Virtualization for Cluster-Based Network Storage Service () A growing concern among corporate information technology (IT) managers is the elevating gap between the increasing system maintenance and administration cost of the IT infrastructure and the decreasing hardware/software acquisition cost. This gap is escalating because system administration and management is still relatively labor-intensive and thus non-scalable, despite extensive research/commercial efforts to automate the process. In view of this trend,commercial enterprises resort to IT out-sourcing in order to share expensive and precious system management expertise. Despite its compelling cost saving advantage, IT out-sourcing so far has not been the mainstream, chiefly because the lack of technology to enforce and certify the so-called Service Level Agreement (SLA) between the out-sourcing and out-sourced parties. This proposal will develop a multi-dimensional storage virtualization system called Stonehenge, which is able to guarantee a wide variety of storage-related Quality of Service (QoS) metrics and thus provides the enabling technology toenforce SLAs associated with storage service in particular and Internet services in general. The set of techniques developed in the Stonehenge system will carry the storage virtualization field one large step further because they allow virtualization of storage resource almost in all possible performance attributes that can be associated with physical disks. As a result, Stonehenge allows creation of virtual disks that are as tangible as physical disks, and yet much more flexible and easier to manage and maintain. As an integral component of this project, we will also develop a unified and reusable implementation framework that could quickly convert, with zero or minor modification, a given cluster-based Internet service into QoS-aware, such that they are capable of supporting contractual SLAs that are described in terms of service-specific performance metrics. Besides its intellectual contributions, this project will make a major impact on the undergraduate and graduate education of the CS department at Stony Brook by introducing a series of system management courses, which will use the Stonehenge prototype as a case study on the functionality and implementation details of production-grade enterprise storage management systems. This project was described byAdmin Istrator (20. June 2011 - 11:49) This project was last edited by Sanja Tumbas (9. July 2012 - 20:35) |