A General Resource Reservation Framework for Scientific Computing

We describe three contributions for distributed resource allocation in scientific applications. First, we present an abstract model in which different resources are represented as tokens of different colors; processes acquire resources by acquiring these tokens. Second, we present distributed scheduling algorithms that allow multiple resource managers to determine custom policies to control allocation of the tokens representing their particular resources. These algorithms allow multiple resource managers, each with its own resource management policy, to collaborate in providing resources for the whole system. Third, we present an implementation of a distributed resource scheduling algorithm framework using our abstract model. This implementation uses Infospheres, which are Internet communication packages written in Java, and shows the benefits of distributing the task of resource allocation to multiple resource managers.

[1]  K. Mani Chandy,et al.  Systematic composition of objects in distributed Internet applications: processes and sessions , 1997, Proceedings of the Thirtieth Hawaii International Conference on System Sciences.

[2]  K. Mani Chandy Parallel program design , 1989 .

[3]  Ian T. Foster,et al.  Globus: a Metacomputing Infrastructure Toolkit , 1997, Int. J. High Perform. Comput. Appl..

[4]  L. Smarr,et al.  Metacomputing : Siggraph'92 Showcase , 1992 .

[5]  David Lifka,et al.  Users guide to the Argonne SP scheduling system , 1995 .

[6]  Miron Livny,et al.  Condor-a hunter of idle workstations , 1988, [1988] Proceedings. The 8th International Conference on Distributed.

[7]  K. Mani Chandy,et al.  A Framework for Structured Distributed Object Computing , 1998, Parallel Comput..

[8]  Andreas Reuter,et al.  Transaction Processing: Concepts and Techniques , 1992 .

[9]  Pattie Maes,et al.  Agents that reduce work and information overload , 1994, CACM.

[10]  K. Mani Chandy,et al.  Parallel program design - a foundation , 1988 .

[11]  Steven J. Plimpton,et al.  Massively parallel methods for engineering and science problems , 1994, CACM.

[12]  David Abramson,et al.  Nimrod: a tool for performing parametrised simulations using distributed workstations , 1995, Proceedings of the Fourth IEEE International Symposium on High Performance Distributed Computing.

[13]  Computer Staff,et al.  Transaction processing , 1994 .