VRM: A Failure-Aware Grid Resource Management System Lars-Olof Burchard, Hans-Ulrich Heiss, Barry Linnert, Joerg Schneider Technische Universitaet Berlin, GERMANY {baron,heiss,linnert,komm}@cs.tu-berlin.de Cesar A. F. De Rose PUCRS, Porto Alegre, BRASIL derose@inf.pucrs.br Keywords: Grid Computing, Failure Recovery, Advance Reservation Reference to this paper should be made as follows: L.-O. Burchard, C. A. F. De Rose, H.-U. Heiss, B. Linnert, J. Schneider (xxxx) ‘VRM: A Failure-Aware Grid Resource Management System’, Int. J. High Performance Computing and Networking, Vol. x, No. x, pp.xxx–xxx. Biographical notes: Lars-Olof Burchard received his diploma in computer science from Paderborn University, Germany, in 1999. From October 1999 to February 2001, he was a member of the research staff and PhD student at the Paderborn Center for Parallel Computing. In March 2001, he joined the communication and operating systems group at Berlin University of Technology, Germany, where he received his doc- torate degree in August 2004. His research interests include distributed multimedia systems, resource management in computer networks and Grid computing. Cesar De Rose is an Associate Professor in the Computer Science Department at the Pontifical Catholic University of Rio Grande do Sul (PUCRS), Porto Alegre, Brazil. His primary research interests are parallel and distributed computing and parallel archi- tectures. He is currently conducting research on a variety of topics applied to clusters and Grids, including resource management, resource monitoring and distributed allo- cation strategies. Dr. De Rose received his doctoral degree in Computer Science from the University Karlsruhe, Germany, in 1998. He currently leads the Research Center in High Performance Computing (CPAD - PUCRS/HP) at PUCRS. Hans-Ulrich Heiss received his diploma and doctorate degrees in computer science from the University of Karlsruhe (Germany) in 1979 and 1987, respectively. 1988-1989 he was a post-doc fellow at IBM T.J. Watson Research in Yorktown Heights (NY), and in 1990 a visiting professor at the University of Helsinki (Finland). After appointments at the universities in Ilmenau and Paderborn (both Germany) he has been a full professor for communication and operating systems at the Berlin University of Technology since 2001. His interests include operating systems, distributed systems, Grid computing, resource management, self-organization, and performance evaluation. Barry Linnert received his diploma in computer science from the Berlin University of Technology, Germany, in 2000. He works as a research assistant at the communication and operating systems group at the Berlin University of Technology. His interests in- clude operating systems, high performance computing, cluster and Grid computing. Joerg Schneider received his diploma in computer science from the Berlin University of Technology (Germany) in 2004. His research interests include resource managment in the Grid, complex co-allocations and especially, Grid workflows. He is currently an research assistant at the communication and operating systems group at the Berlin University of Technology. 1