[Pw_forum] forrtl: severe (174): SIGSEGV, segmentation fault occurred

James J Ramsey jjr19 at zips.uakron.edu
Sat Sep 26 03:33:11 CEST 2009


2009/9/25 Q.J.Wang <wangqj1 at 126.com>:
> Dear all
> According to people's advice ,I had checked it ,the reason of memory was
> ruled out .I task I run is a small system .With K-points division it can
> finish the task ,while with R G division, it can't. and turns up :
>
> node1
> forrtl: severe (174): SIGSEGV, segmentation fault occurred
> Image              PC                Routine            Line
> Source
> mca_pml_ob1.so     00007F34DE43BB56  Unknown               Unknown  Unknown
> mca_pml_ob1.so     00007F34DE43C268  Unknown               Unknown  Unknown
> mca_btl_sm.so      00007F34DDC2102D  Unknown               Unknown  Unknown
> libopen-pal.so.0   00007F34E25ECFC9  Unknown               Unknown  Unknown
> mca_pml_ob1.so     00007F34DE43803C  Unknown               Unknown  Unknown
> libmpi.so.0        00007F34E2B306E0  Unknown               Unknown  Unknown
> libmpi_f77.so.0    00007F34E2DCFB94  Unknown               Unknown  Unknown
> pw.x               000000000051F1BA  Unknown               Unknown  Unknown
> pw.x               000000000067389F  Unknown               Unknown  Unknown
> pw.x               0000000000663521  Unknown               Unknown  Unknown
> pw.x               0000000000664647  Unknown               Unknown  Unknown
> pw.x               0000000000595B60  Unknown               Unknown  Unknown
> pw.x               00000000004629DB  Unknown               Unknown  Unknown
> pw.x               00000000004627CC  Unknown               Unknown  Unknown
> libc.so.6          00007F34E180C586  Unknown               Unknown  Unknown
> pw.x               00000000004626C9  Unknown               Unknown  Unknown
> --------------------------------------------------------------------------
> mpirun has exited due to process rank 4 with PID 6302 on
> node node1 exiting without calling "finalize". This may
> have caused other processes in the application to be
> terminated by signals sent by mpirun (as reported here).
>
> Any advice will be appreciated !

What implementation of MPI are you using, and what version? For
example, are you using MPICH 1.2.7 or OpenMPI 1.3?


More information about the users mailing list