That didn't come from OMPI - that error message is from LAM-MPI, which no longer is supported.

I suggest you check the default path being set by Torque - looks like it is picking up an old LAM install.

On Jun 30, 2011, at 8:24 PM, zhuangchao wrote:

hello  all ,
     I  submited  the following  Torque/pbs script. 
     #PBS -e /tmp/blast_19297.err
     #PBS -o /tmp/blast.output
     mpiexec  -d -machinefile  /tmp/nodes.19297.txt   -np  3  /data1/bin/mpiblast  -p tblastx -i /data1/cluster/sequences/seq_4.txt -d nt -o /data1/cluster/blast.out/blast.out.19297      -g T -m  0 -F F
     Then  I  got  the following error  from openmpi.   But  it is ok if I run the above mpiexec command 
in the bash shell.  Can you  help me ?  Thank you very much !  
n-1<18242> ssi:boot:base: looking for boot schema in following directories:
n-1<18242> ssi:boot:base:   <current directory>
n-1<18242> ssi:boot:base:   $TROLLIUSHOME/etc
n-1<18242> ssi:boot:base:   $LAMHOME/etc
n-1<18242> ssi:boot:base:   /data1/lam-mpi/etc
n-1<18242> ssi:boot:base: looking for boot schema file:
n-1<18242> ssi:boot:base:   /tmp/nodes.19297.txt
n-1<18242> ssi:boot:base: found boot schema: Not found!
The hostfile "/tmp/nodes.19297.txt" could not be found:
        Unix errno: 2
        No such file or directory
Things to check:
        - ensure that the file exists
          try "ls -l /tmp/nodes.19297.txt"
        - ensure that you have read permissions on the file
          try "cat /tmp/nodes.19297.txt"
It seems that there is no lamd running on the host node2.
This indicates that the LAM/MPI runtime environment is not operating.
The LAM/MPI runtime environment is necessary for the "lamhalt" 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.
users mailing list