Kerrighed: A Single System Image Cluster Operating System for High Performance Computing
Kerrighed is a single system image operating system for clusters. Kerrighed aims at combining high performance, high availability and ease of use and programming. Kerrighed implements a set of global resource management services that aim at making resource distribution transparent to the applications, at managing resource sharing in and between applications and at taking benefit of the whole cluster resources for demanding applications. Kerrighed is implemented as a set of modules extending the Linux kernel. Legacy multi-threaded applications and message-passing based applications developed for an SMP PC running Linux can be executed without re-compilation on a Kerrighed cluster. The proposed demonstration presents a prototype of Kerrighed running on a cluster of four portable PCs. It shows the main features of Kerrighed in global memory, process and stream management by running multi-threaded and MPI applications on top of Kerrighed.
KeywordsShared Memory Parallel Application Cluster Node Processor Load Global Scheduler
Unable to display preview. Download preview PDF.
- 1.Hobbs, M.J., Goscinski, A.M., Silock, J.: Genesis: The operating system managing parallelism and providing single system image on cluster. Technical Report TR C00/03, School of Computing and Mathematics, Deakin University (February 2000)Google Scholar
- 2.Badrinath, R., Morin, C.: Common mechanisms for supporting fault tolerance in DSM and message passing systems. Rapport de recherche 4613, INRIA (November 2002)Google Scholar
- 4.Lottiaux, R., Morin, C.: Containers: A sound basis for a true single system image. In: Proceeding of IEEE International Symposium on Cluster Computing and the Grid (CCGrid 2001), Brisbane, Australia, May 2001, pp. 66–73 (2001)Google Scholar
- 5.Morin, C., Gallard, P., Lottiaux, R., Vallée, G.: Towards an efficient single single system image cluster operating system. In: ICA3PP (2002)Google Scholar
- 6.Vallée, G., Morin, C., Berthou, J.-Y., Rilling, L.: A new approach to configurable dynamic scheduling in clusters based on single system image technologies. In: International Parallel and Distributed Processing Symposium (April 2003)Google Scholar
- 7.Vallée, G., Morin, C., Berthou, J.-Y., Malen, I.D., Lottiaux, R.: Process migration based on Gobelins distributed shared memory. In: Proc. of the workshop on Distributed Shared Memory (DSM 2002) in CCGRID 2002, Berlin, Allemagne, May 2002, pp. 325–330. IEEE Computer Society, Los Alamitos (2002)Google Scholar