Hi, all<br><br>In fact, I can not sure whether Torque or mpich cause this problem. I just express my problem as follow a exapmle script:<br>#!/bin/bash<br>### Job name<br>#PBS -N name<br>#PBS -q batch<br>### number of numbers and process per node<br>
#PBS -l nodes=2:ppn=4<br>### Job's error output <br>#PBS -e error<br>### Job's general output<br>#PBS -o stdout<br><br>cd $PBS_O_WORKDIR<br>echo "Job begin at "`date`<br># program examples<br>mpiexec -n 8 $PBS_O_WORKDIR/cpi<br>
echo "Job stop at "`date`<br><br>exit 0<br><br>cpi is a example progrm in mpich package. Our cluster profile is two processors with every 4 cores, i.e. 8 cores per one node. But the message from the above job is as follow when i submit this job:<br>
Process 0 on node5<br>Process 1 on node5<br>Process 2 on node5<br>Process 3 on node5<br>Process 5 on node5<br>Process 6 on node5<br>Process 4 on node5<br>Process 7 on node5 <br><br>All processes are ran on one node, but i allocated 2 nodes. I don't know what cause it happen, and how to solve it.<br>
Thanks<br><br>PS: Torque version:2.4.6, mpich:2-1.1.1p1, mpiexec:0.83<br>--<br>Best Wishes <br>ChenWeiguang<br><br>************************************************<br># Chen, Weiguang <br>#<br># Postgraduate, Ph. D<br>
# 75 University Road, Physics Buliding # 218<br># School of Physics & Engineering<br># Zhengzhou University<br># Zhengzhou, Henan 450052 CHINA<br>#<br># Tel: 86-13203730117;<br># <a href="mailto:E-mail%3Achenweiguang82@gmail.com">E-mail:chenweiguang82@gmail.com</a>;<br>
# <a href="mailto:chenweiguang82@qq.com">chenweiguang82@qq.com</a><br>#<br>**********************************************<br><br>