A Network-Aware Grid for Efficient Parallel Monte Carlo Simulation of Coagulation Phenomena
Remote instrumentation services often rely on distributed control and computation. In this framework, a grid infrastructure offers the opportunity to utilize massive memory and computing resources for the storage and processing of data generated by scientific equipment. The provision of grid-enabled remote instrumentation services is also a key challenge for high-speed next generation networks and cross-layer mechanisms, between grid middleware and network protocols, should be introduced to support quality of service (QoS) both at network and at application layers. This chapter is mainly focused on distributed data computation and, more in detail, on the optimization of the time necessary to perform a simulation concerning particles coagulation phenomena. Extensive computations have been performed in a cluster environment and the collected data have been used as a starting point for the dimensioning of a proper grid infrastructure. Since computations are characterized by frequent data exchanges, this chapter investigates how bandwidth allocation affects overall performance.
KeywordsDSMC GNRB Dynamic resource allocation MPLS-TE
The work was supported by RFBR grants No. 06-01-00586 and No. 06-01-00046, President grant No. 587.2008.1 of “Leading scientific schools” program, INTAS grant No. 05-109-5267, Russian Science Support Foundation grant, RINGRID EU FP6 Project.
- 1.D. Adami, C. Callegari, S. Giordano, and M. Pagano. A new path computation algorithm and its implementation in NS2. In IEEE International Conference on Communications, Glasgow, Scotland, 2007, pp. 24–28, Jun. 2007.Google Scholar
- 2.D. Adami, N. Carlotti, S. Giordano, and M. Repeti. Design and development of a GNRB for the coordinated use of network resources in a high performance grid environment. In F. Davoli, S. Palazzo, and S. Zappatore, editors, Distributed Cooperative Laboratories: Networking, Instrumentation, and Measurements, pp. 295–307, Springer, New York, 2006.CrossRefGoogle Scholar
- 3.M. Baker, R. Buyya, and D. Laforenza. Grids and Grid technologies for wide-area distributed computing. Software–Practice and Experience Journal, 2002.Google Scholar
- 4.I. Foster, C. Kesselman, J. Nick, and S. Tuecke. The physiology of the Grid: An open Grid services architecture for distributed systems integration, June 2002. http://www.globus.org/research/papers/ogsa.pdf
- 5.I. Foster, C. Kesselman, and S. Tuecke. The anatomy of the grid: Enabling scalable virtual organization. International Journal of Supercomputer Applications, 2001. http://www.globus.org/research/papers/anatomy.pdf
- 6.F. Le Faucheur, L. Wu, B. Davie, S. Davari, P. Vaananen, R. Krishnan, P. Cheval, and J. Heinanen. Multi-Protocol label switching (MPLS) support of differentiated services. In RFC 3270, May 2002.Google Scholar
- 8.E. Rosen, A. Viswanathan, and R. Callon. Multiprotocol label switching architecture. In RFC 3031, Jan. 2001.Google Scholar
- 9.The OSPF–TE Network Simulator Home Page. http://netgroup-serv.iet.unipi.it/ospf-te_ns/
- 10.The RSVP–TE Network Simulator Home Page. http://netgroup-serv.iet.unipi.it/rsvp-te_ns/