[petsc-users] Debug AOCreateBasic

[Rongliang Chen]

Hi Jed,

I  have not find a way to "dump core on selected ranks" yet and I will 
continue to do that. I run my code with the option 
"-on_error_attach_debugger" and got the following message:

--------------------------------------------------------------------------
An MPI process has executed an operation involving a call to the
"fork()" system call to create a child process.  Open MPI is currently
operating in a condition that could result in memory corruption or
other system errors; your MPI job may hang, crash, or produce silent
data corruption.  The use of fork() (or system() or other calls that
create child processes) is strongly discouraged.

The process that invoked fork was:

   Local host:          node1529 (PID 3701)
   MPI_COMM_WORLD rank: 0

If you are *absolutely sure* that your application will successfully
and correctly survive a call to fork(), you may disable this warning
by setting the mpi_warn_on_fork MCA parameter to 0.
--------------------------------------------------------------------------
[node1529:03700] 13 more processes have sent help message 
help-mpi-runtime.txt / mpi_init:warn-fork
[node1529:03700] Set MCA parameter "orte_base_help_aggregate" to 0 to 
see all help / error messages
--------------------------------------------------------------------------

Is this message useful for the debugging?

Best,
Rongliang

On 11/06/2013 01:22 PM, Jed Brown wrote:
> Rongliang Chen <rongliang.chan at gmail.com> writes:
>
>> Hi Jed,
>>
>> I tested my code on a locally 16-cores workstation. Both the MPICH and
>> OPENMPI version work well for the  30 million unstructured meshes case
>> (this workstation has 256G memory).
> Then I would start thinking about an MPI problem and see if you can
> configure to get a core dump.
>
>> My code is also valgrind-clean on this workstation.
> Good.