Hello,<div><br></div><div>I was using <meta http-equiv="content-type" content="text/html; charset=utf-8">the sge6.01u4 to runs some serial jobs for some time.<br><div><br></div><div>The cluster I am using has 8+1 nodes with Opteron procs. </div>
<div><br></div><div>I wanted to take advantage of this as the software I am using has a parallel version.</div></div><div>So I've installed mpich2 as the parallel enviroment, I've activated the mpd demon. when doing mpdtrace -l it sees all the 8 nodes(slave) + 1 headnode</div>
<div>Now when I am submitting the job using this script:</div><div><br></div><div><div>#!/bin/bash</div><div>#$ -S /bin/bash</div><div>#$ -o test.log</div><div>#$ -e test.err</div><div>#$ -N TEST_Parallel</div><div>#$ -pe mpich 2</div>
<div>#$ -cwd</div><div><br></div><div>mpiexec -n $NSLOTS siesta <input> output </div></div><div><br></div><div>the scheduler submits the job, when doing qstat I see that it's running but no output is produced, and this will go on for days, nothing happens, the job will stay in the queue with status "r" forever.</div>
<div>the only info i get is in the test.log file is:</div><div><br></div><div><div>-catch_rsh /home/sge6.01u4/default/spool/cn105/active_jobs/4049.1/pe_hostfile</div><div>cn105</div><div>cn102</div></div><div> </div><div>
so it seems that the scheduler did the job </div><div>nothing in the test.err, the output is created, but it's empty.</div><div>the nodes are from cn101 to cn108</div><div><br></div><div><br></div><div>The serial version works fine, this is the script I am using</div>
<div><br></div><div><meta http-equiv="content-type" content="text/html; charset=utf-8"><div>#!/bin/bash</div><div>#$ -S /bin/bash</div><div>#$ -o test.log</div><div>#$ -e test.err</div><div>#$ -N TEST</div><div>#$ -cwd</div>
<div><br></div><div> siesta <input> output </div></div><div><br></div><div><br></div><div> I may have missed something during the instalation of mpich2.</div><div><br></div><div>Maybe some of you encountered similar problems, any ideas are welcomed.</div>
<div><br></div><div>Thanks,</div><div>Eli</div>