Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list

Subject: [OMPI users] OpenMPI checkpoint/restart
From: Sai Sudheesh (saisudheesh_at_[hidden])
Date: 2010-11-04 05:39:58


Hi All,

I am experimenting with the openMPI checkpoint and restart mechanism.
I have installed blcr-0.8.2 in /usr directory of Redhat linux system,RHEL 5
(2.6..18-164.el5).
I have unpacked openmpi-1.4.2 to /usr and installed.

while configuring openMPI I used the following commands
#./configure --with-blcr=cr --enable-ft-thread --enable-mpi-threads
--with-blcr=/usr/local --with-blcr-libdir=/usr/local/lib
#make
#make install

after this i tried to run my application
using
#mpirun -np 4 -am ft-enable-cr a.out

then I got the following error
---------------------------------------------------------------------
It lools like MPI_INIT failed for some reason; your parallel process is
likely to abort. There are many
reasons that a parallel process can fail during MPI_INIT; some of due to
configuration or
environment problems. This failure appears to be internal failure; here is
some additionan information(which may only relevant to an openMPI
developer);

 ompi-mpi_ini:orte_init failed
-->Returned "Error" (-1) instead of "Success"(0)
[localhost.localdomain:28655][[INVALID,INVALID] ORTE_ERROR_LOG:Errorin file
runtime/orte_init.c at line 77

***The MPI-Init() function was called before MPI_INIT was invoked.
***This is disallowed by MPI standard.
***Your MPI job will now abort
[localhost.localdomain]Abort before MPI_INIT completed successfully; not
able to guarantee that all other process are killed!

-------------------------------------------------------------------------

section 1 of the error mesage was repeated many times..

What may went wrong with this?
How can I resolve this?

regards
sai sudheesh