[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Condor-users] Does condor support MPICH2?



Dear condor users,

     Condor is installed on one Windows XP machine ( No Linux). Sample
C programs (serial) run fine, but MPI (MPICH2) program fails always.
Either with Parallel or MPI universes.

     Does condor support MPICH2? or it support only MPICH ?

Job submission is done through 2 files: mpi.sub, mpi.cmd

E:\condor\job>type mpi.sub

Executable      = e:\condor\job\mpi.cmd
#arguments       = -n 1 e:\condor\job\cpi.exe < e:\condor\job\input > e:\condor\
job\out.mpi
Universe        = parallel
output          = mpi.out
error           = mpi.err
log             = mpi.log
machine_count   = 1
queue

E:\condor\job>type mpi.cmd
e:\mpich2\bin\mpiexec -n 1 e:\condor\job\cpi.exe <e:\condor\job\input >e:\condor
\job\mpi.output

E:\condor\job>condor_submit mpi.sub
Submitting job(s).
Logging submit event(s).
1 job(s) submitted to cluster 15.

E:\condor\job>condor_q


-- Submitter: support-2.XXXX : <10.129.150.51:1120> : support-2.XXXX
 ID      OWNER            SUBMITTED     RUN_TIME ST PRI SIZE CMD
  15.0   Administrator   3/23 16:01   0+00:00:00 I  0   0.0  mpi.cmd

1 jobs; 1 idle, 0 running, 0 held

E:\condor\job>condor_q -analyze


-- Submitter: support-2.XXXX : <10.129.150.51:1120> : support-2.XXXX
 ID      OWNER            SUBMITTED     RUN_TIME ST PRI SIZE CMD
---
015.000:  Run analysis summary.  Of 1 machines,
      0 are rejected by your job's requirements
      0 reject your job because of their own requirements
      0 match but are serving users with a better priority in the pool
      1 match but reject the job for unknown reasons
      0 match but will not currently preempt their existing job
      0 are available to run your job

1 jobs; 1 idle, 0 running, 0 held

E:\condor\job>

If MPI universe is used - it asks for mpich.dll.

Please help me to know what am doing wrong here. Any additional config
needs to be done?

Thanks in advance,
Sangamesh