VIDAS: object-based virtualized data sharing for high performance storage I/O.

ABSTRACTWith scientific computing in the cloud gaining popularity and using every time larger data sets, high performance storage I/O in virtualized environments is substantially increasing in importance. However, exploiting the performance potential of the storage I/O on today's virtualized architectures is complex, due to the limitations of POSIX standard for storage I/O and the lack of integration of related mechanisms such as data sharing, storage I/O coordination, relaxing the consistency semantics, and data locality awareness. In this paper we propose VIDAS (Virtualized DAta Sharing), an object-based virtualized data store that targets to integrate the above mechanisms through a simple and powerful interface. VIDAS can be used to efficiently and consistently share access to externally stored data in virtualized environments based on a shared pool of storage objects. We show how VIDAS can be used for straightforwardly implementing I/O coordination and data sharing for two common high-performance patterns: inter-domain write-reader and inter-domain collective I/O. We present the implementation and evaluation of VIDAS for the Xen virtualization solution. In addition, we present a novel mechanism for efficiently sharing memory among an arbitrary number of virtual machines.