Expanding Windows Kernel to Integrate Heterogeneous Storage Resources on Data Grids

摘要

The usage of data servers to provide storage capabilities in grids has grown in popularity during the last years, but existing solutions are centred in grid-Unix environments and in the usage of specific I/O libraries and servers. The philosophy behind grid is to use idle resources to achieve a higher level of computational services (computation, storage, etc). But in most enterprises and universities, the common platform is Windows, thus to take advantage of those resources solutions are needed for Windows platforms. The proposed grid solution integrates available data network solutions (NFS, CIFS, WebDAV) and makes possible the access to a global grid file system. Our solution differs from others because it does not need the installation of new data servers with new protocols Moreover, most existing data grid solutions provide new I/O APIs, thus forcing the users to rewrite or to recompile their applications. The proposed solution is based on Windows kernel mechanisms, so the user can execute their applications as usual. The integration in the kernel provides better performance that user library solutions, and allows the usage of kernel mechanisms as system cache in a more flexible way.