<div dir="ltr">OpenMPI is broken again.<div><br></div><div>We could:</div><div><br></div><div> a) put in a define for OpenMPI and then disable this in C</div><div><br></div><div> b) put in a flag for OpenMPI and then disable this in Python</div><div><br></div><div> c) try to code up a failing (hanging) test in configure</div><div><br></div><div>Other suggestions?</div><div><br></div><div> Matt</div><div><br><div class="gmail_quote">---------- Forwarded message ----------<br>From: <b class="gmail_sendername">Patrick Begou</b> <span dir="ltr"><<a href="mailto:Patrick.Begou@legi.grenoble-inp.fr">Patrick.Begou@legi.grenoble-inp.fr</a>></span><br>Date: Fri, Jan 6, 2017 at 10:08 AM<br>Subject: Re: [petsc-users] [SOLVED] make test freeze<br>To: Matthew Knepley <<a href="mailto:knepley@gmail.com">knepley@gmail.com</a>><br>Cc: PETSc <<a href="mailto:petsc-users@mcs.anl.gov">petsc-users@mcs.anl.gov</a>><br><br><br>Hi Matthew,<br>
<br>
Using the debuguer I finaly found the problem. It is related to MPI. In src/sys/objects/pinit.c line 779, petsc test the availability of PETSC_HAVE_MPI_INIT_THREAD and this is set to True beccause my OpenMPI version is compiled with --enable-mpi-thread-multiple.<br>
However the call to MPI_Init_thread(argc,args,MPI_<wbr>THREAD_FUNNELED,&provided) hangs and freeze the application.<br>
<br>
Unsetting PETSC_HAVE_MPI_INIT_THREAD in petsc solves the problem.<br>
<br>
I remember a HPC seminar on BULLX systems where they give us some informations about known problems whith the MPI_Init_thread call in openMPI. May be I should use a more recent version of OpenMPI. This also explain why I had this problem with previous versions of petsc (same OpenMPI environment).<br>
None of our codes mixes OpenMP and MPI.... so I never fall in this situation in production and petsc always behave fine (excepted for make test).<br>
<br>
Is there a way to turn off PETSC_HAVE_MPI_INIT_THREAD at configure time for Petsc ? I've manualy removed it in the generated petscconf.h file before compiling Petsc in debug mode but I don't think it is the best way to to this.....<br>
<br>
Thanks for your help in running separatly the test codes.<span class="gmail-HOEnZb"><font color="#888888"><br>
<br>
Patrick<br>
<br>
-- <br>
==============================<wbr>==============================<wbr>=======<br>
| Equipe M.O.S.T. | |<br>
| Patrick BEGOU | mailto:<a href="mailto:Patrick.Begou@grenoble-inp.fr" target="_blank">Patrick.Begou@grenoble-<wbr>inp.fr</a> |<br>
| LEGI | |<br>
| BP 53 X | Tel 04 76 82 51 35 |<br>
| 38041 GRENOBLE CEDEX | Fax 04 76 82 52 71 |<br>
==============================<wbr>==============================<wbr>=======<br>
<br>
</font></span></div><br><br clear="all"><div><br></div>-- <br><div class="gmail_signature">What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead.<br>-- Norbert Wiener</div>
</div></div>