[GE users] qsub not finding lam

Reuti reuti at staff.uni-marburg.de
Mon Jun 4 19:26:23 BST 2007


Am 04.06.2007 um 19:58 schrieb Margaret Doll:

> I am having trouble with qsub working after I rebuilt mpich compilers.
>
> Created lamhosts in my home directory.
>
> recon -v lamhosts
> n-1<4958> ssi:boot:base:linear: booting n0 (ted.chem.brown.edu)
> n-1<4958> ssi:boot:base:linear: booting n1 (compute-0-0)
> n-1<4958> ssi:boot:base:linear: booting n2 (compute-0-1)
> n-1<4958> ssi:boot:base:linear: booting n3 (compute-0-2)
> n-1<4958> ssi:boot:base:linear: booting n4 (compute-0-3)
> n-1<4958> ssi:boot:base:linear: finished
>
> lamboot -v lamhosts             was successful

Please have a look here:

http://gridengine.sunsource.net/howto/lam-integration/lam- 
integration.html

-- Reuti


> tping -c1 N
>   1 byte from 4 remote nodes and 1 local node: 0.001 secs
>
> 1 message, 1 byte (0.001K), 0.001 secs (1.366K/sec)
> roundtrip min/avg/max: 0.001/0.001/0.001
>
>
> mpif90 mpiprogram.f -o mpiprogram
>
> where mpif90 is a compiler built based on Portland Group Compilers  
> with the following options:
>
> export CC=pgcc
> export CXX=pgCC
> export F77=pgf77
> export F90=pgf90
> ./configure -c++=pgCC -cc=pgcc -fc=pgf77 \
> > -cflags="-Msignextend -tp px -DUSE_U_INT_FOR_XDR - 
> DHAVE_RPC_RPC_H=1" \
> > -opt=-fast -fflages="-tp px" \
> > -c++flags="-tp px" -f90flags="-tp px" -f90=pgf90 --enable-f77 -- 
> enable-f90modules
> \--with-comm=shared
>
>
> qsub -q test.q -pe mpich 8 ./mpishell
> Your job 265 ("mpishell") has been submitted
>
> where mpishell contains
>
> #!/bin/bash
> #$ -cwd
> mpirun mpi -c 8  -machinefile /home/mad/machines /home/mad/freeman/ 
> mpiprogram
>
>
> and machines contains
>
> compute-0-3
> compute-0-3
> compute-0-3
> compute-0-3
>
> compute-0-3 is contained in the test.q queue and has  8 slots or  
> processors.
>
> The program does not run when submitted with "qsub"
>
>
> more mpishell.e266
> ---------------------------------------------------------------------- 
> -------
> It seems that there is no lamd running on the host compute-0-3.local.
>
> This indicates that the LAM/MPI runtime environment is not operating.
> The LAM/MPI runtime environment is necessary for the "mpirun" command.
>
> Please run the "lamboot" command the start the LAM/MPI runtime
> environment.  See the LAM/MPI documentation for how to invoke
> "lamboot" across multiple machines.
> ---------------------------------------------------------------------- 
> -------
>
> lamd is running on the head node and the compute nodes.
>
> mpirun works, but I need qsub to work.
>
> mpirun -v -np 8 mpiprogram
> running /home/mad/freeman/mpiprogram on 8 LINUX ch_p4 processors
> Created /home/mad/freeman/PI5031
> MY ID is            0 OUT OF            8 BELONGING TO GROUP
> MY ID is            6 OUT OF            8 BELONGING TO GROUP
> MY ID is            4 OUT OF            8 BELONGING TO GROUP
> MY ID is            2 OUT OF            8 BELONGING TO GROUP
> MY ID is            5 OUT OF            8 BELONGING TO GROUP
> MY ID is            7 OUT OF            8 BELONGING TO GROUP
> MY ID is            1 OUT OF            8 BELONGING TO GROUP
> MY ID is            3 OUT OF            8 BELONGING TO GROUP
>
>
>
>
>
>
>
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
> For additional commands, e-mail: users-help at gridengine.sunsource.net

---------------------------------------------------------------------
To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
For additional commands, e-mail: users-help at gridengine.sunsource.net




More information about the gridengine-users mailing list