[petsc-users] Bad Termination error in MatPartitioningApply with ParMETIS

[Smith, Barry F.]

  Can you please send use the exact code and data file that causes the crash? And any options.

  There are bugs in Metis/Parmetis that we need to track down and eliminate since it is so central to PETSc's work flow.

    Barry


> On Dec 18, 2019, at 4:21 AM, Eda Oktay <eda.oktay at metu.edu.tr> wrote:
> 
> Hi all,
> 
> I am trying to partition a matrix in multiple processes. However, at some point I get the following eror:
> 
> [ 0] ***ASSERTION failed on line 176 of file /home/edaoktay/petsc-3.11.1/arch-linux2-c-debug/externalpackages/git.parmetis/libparmetis/comm.c: j == nnbrs
> [ 2] [ 3] ***ASSERTION failed on line 176 of file /home/edaoktay/petsc-3.11.1/arch-linux2-c-debug/externalpackages/git.parmetis/libparmetis/comm.c: j == nnbrs
> enson_unweighted_yeni_vertexweight_imbalance_without_spectral: /home/edaoktay/petsc-3.11.1/arch-linux2-c-debug/externalpackages/git.parmetis/libparmetis/comm.c:176: libparmetis__CommSetup: Assertion `j == nnbrs' failed.
> enson_unweighted_yeni_vertexweight_imbalance_without_spectral: /home/edaoktay/petsc-3.11.1/arch-linux2-c-debug/externalpackages/git.parmetis/libparmetis/comm.c:176: libparmetis__CommSetup: Assertion `j == nnbrs' failed.
> ***ASSERTION failed on line 176 of file /home/edaoktay/petsc-3.11.1/arch-linux2-c-debug/externalpackages/git.parmetis/libparmetis/comm.c: j == nnbrs
> enson_unweighted_yeni_vertexweight_imbalance_without_spectral: /home/edaoktay/petsc-3.11.1/arch-linux2-c-debug/externalpackages/git.parmetis/libparmetis/comm.c:176: libparmetis__CommSetup: Assertion `j == nnbrs' failed.
> 
> ===================================================================================
> =   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
> =   PID 13751 RUNNING AT d1e.wls.metu.edu.tr
> =   EXIT CODE: 134
> =   CLEANING UP REMAINING PROCESSES
> =   YOU CAN IGNORE THE BELOW CLEANUP MESSAGES
> ===================================================================================
> YOUR APPLICATION TERMINATED WITH THE EXIT STRING: Aborted (signal 6)
> This typically refers to a problem with your application.
> Please see the FAQ page for debugging suggestions
> 
> I get the error for example in 9*9 matrix for 4 processes. Why a I getting this message, it is working with 2 processes for all matrices but when I increase process number, it starts to give this message at some point.
> 
> Thanks!
> 
> Eda