error may related to open mpi

[bruceyoung01]

hi all
I am using open mpi to run a parallel job. But got the following error.

bash-3.2$ mpirun -np 1 ./real.exe
forrtl: severe (174): SIGSEGV, segmentation fault occurred
Image PC Routine Line Source
real.exe 000000010BAFF001 Unknown Unknown Unknown
real.exe 000000010BAFD681 Unknown Unknown Unknown
real.exe 000000010BAD8B51 Unknown Unknown Unknown
real.exe 000000010BA695BA Unknown Unknown Unknown
real.exe 000000010BA74822 Unknown Unknown Unknown
libsystem_platfor 00007FFF911DF5AA Unknown Unknown Unknown
libmpi.1.dylib 0000000111A3D55B Unknown Unknown Unknown
mca_pml_bfo.so 00000001126420A1 Unknown Unknown Unknown
libmpi.1.dylib 00000001122E0B15 Unknown Unknown Unknown
libmpi.1.dylib 000000011225AF8C Unknown Unknown Unknown
libmpi.1.dylib 00000001121F6BDB Unknown Unknown Unknown
libmpi.1.dylib 000000011220F530 Unknown Unknown Unknown
libmpi_f77.1.dyli 00000001118BDB87 Unknown Unknown Unknown
real.exe 0000000109E5DB6F Unknown Unknown Unknown
real.exe 000000010A853D79 Unknown Unknown Unknown
real.exe 000000010937273D Unknown Unknown Unknown
real.exe 0000000109335786 Unknown Unknown Unknown
--------------------------------------------------------------------------
mpirun has exited due to process rank 0 with PID 52368 on
node modis.local exiting improperly. There are two reasons this could occur:

1. this process did not call "init" before exiting, but others in
the job did. This can cause a job to hang indefinitely while it waits
for all processes to call "init". By rule, if one process calls "init",
then ALL processes must call "init" prior to termination.

2. this process called "init", but exited without calling "finalize".
By rule, all processes that call "init" MUST call "finalize" prior to
exiting or it will be considered an "abnormal termination"

This may have caused other processes in the application to be
terminated by signals sent by mpirun (as reported here).
—————————————————————————————————————
I am not sure which reason caused this error. Is there any suggestions?

Thank you
Bruce

 

[xwb]

Hard to tell without looking at the code. SIGSEGV can be caused by anything. No need to show us everything: just until the init.

 

[bruceyoung01]

What's the meaning of "No need to show us everything: just until the init.

 

[xwb]

You don't need to dump the entire program: just from the beginning of the main program to the part where you do the mpi init. We'll ask you for more bits if we need to see them.