Use of the parallel port to measure MPI intertask communication costs in COTS PC clusters

Performance analysis of system time parameters is important for the development of parallel and distributed programs because it provides a means of estimating program execution times and it is important for scheduling tasks on processors. Measuring time intervals between events occurring in different nodes of COTS clusters of workstations is not a trivial task due to the absence of a unified clock view. We propose a different approach to measure system time parameters and program performance in clusters with the aid of the parallel port present in every machine of a COTS cluster. Some experimental values of communication delays using the MPI library in a Linux PC cluster are presented and the efficiency and precision of the proposed mechanism are analyzed.

[1]  Bruno Raffin,et al.  Comparing the communication performance and scalability of a Linux and a NT cluster of PCs, a Cray origin 2000, an IBM SP and a Cray T3E-600 , 1999, ICWC 99. IEEE Computer Society International Workshop on Cluster Computing.

[2]  Parameswaran Ramanathan,et al.  Hardware-Assisted Software Clock Synchronization for Homogeneous Distributed Systems , 1990, IEEE Trans. Computers.

[3]  Emmanuelle Anceaume,et al.  Performance Evaluation of Clock Synchronization Algorithms , 1998 .

[4]  David B. Skillicorn,et al.  Performance Results for a Reliable Low-Latency Cluster Communication Protocol , 1999, IPPS/SPDP Workshops.

[5]  Amotz Bar-Noy,et al.  Designing broadcasting algorithms in the postal model for message-passing systems , 2005, Mathematical systems theory.

[6]  Jorji Nonaka,et al.  Low-Cost Hybrid Internal Clock Synchronization Mechanism for COTS PC Cluster (Research Note) , 2002, Euro-Par.

[7]  Martin Horauer.  Hardware Support for Clock Synchronization in Distributed Systems , 2001 .

[8]  Henry G. Dietz,et al.  PAPERS: Purdue's Adapter for Parallel Execution and Rapid synchronization , 1994 .

[9]  Leslie G. Valiant,et al.  A bridging model for parallel computation , 1990, CACM.

[10]  Ramesh Subramonian,et al.  LogP: towards a realistic model of parallel computation , 1993, PPOPP '93.

[11]  Chris J. Scheiman,et al.  LogGP: incorporating long messages into the LogP model—one step closer towards a realistic model for parallel computation , 1995, SPAA '95.