[Paraview] 3.98 MPI_Finalize out of order in pvbatch

[Burlen Loring]

yeah it's a strange one....

The clues we have at this point are the 5 ctests that have been failing 
on the nautilus dashboard. 
http://open.cdash.org/viewTest.php?onlyfailed&buildid=2719388, and 
3.14.1 doesn't have the issue (it's still running OK).

I'll see if I can narrow down when the issue started, and if the mpi  
binaries have debugging symbols I will see if I can walk through.

On 12/18/2012 11:42 AM, Utkarsh Ayachit wrote:
> That's really odd. Looking at the call stacks, it looks like the the
> code on both processes is at the right location: both are calling
> MPI_Finalize(). I verified that MPI_Finalize() does indeed gets called
> once (by adding a break point on MPI_Finalize in pvbatch). Burlen, can
> you peek into the files (finalize.c, adi.c etc.) to see if we can spot
> why the two processes diverge?
>
> Utkarsh
>
> On Fri, Dec 7, 2012 at 3:13 PM, Burlen Loring<bloring at lbl.gov>  wrote:
>> #5  0x00002b073a2e3c04 in PMPI_Finalize () at finalize.c:27