Highly available and scalable Grid services

Researchers who build Grid computing infrastructures constantly face scalability issues, both at the system-level of the Grid's internals and at the user-level to support complex end-user applications. XtreemOS is an E.U. research project that aims at "Building and Promoting a Linux-based Operating System to Support Virtual Organizations for Next Generation Grids". One of the explicit goals of the project is to address scalability issues by abstracting these issues as much as possible from the internal implementation of the system. This is an ambitious goal, since in the most general case scalability issues must be addressed within each component of a distributed system. To a certain extent, it is possible to build scalable abstractions that allow other programmers to build system-level and application-level functionalities while giving less thought to scalability issues. This paper discusses a number of highly available and scalable Grid services that are being built to support this idea. They can be classified in three separate categories: (i) services to store/query structured data in a scalable fashion; (ii) services to communicate in a scalable fashion; (iii) services to (partially) hide the effects of scale.