<div dir="ltr"><div class="gmail_extra"><div class="gmail_quote">On Wed, Oct 1, 2014 at 9:32 AM, Barry Smith <span dir="ltr"><<a href="mailto:bsmith@mcs.anl.gov" target="_blank">bsmith@mcs.anl.gov</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex"><br>
Recommend running under valgrind. <a href="http://www.mcs.anl.gov/petsc/documentation/faq.html#valgrind" target="_blank">http://www.mcs.anl.gov/petsc/documentation/faq.html#valgrind</a></blockquote><div><br></div><div>Barry, it looks like this commit introduced it</div><div><br></div><div> <a href="https://bitbucket.org/petsc/petsc/commits/7be6b909d0172a4ed9ffbe3833ba966bb47c2681#Lsrc/ksp/pc/impls/ml/ml.cT422">https://bitbucket.org/petsc/petsc/commits/7be6b909d0172a4ed9ffbe3833ba966bb47c2681#Lsrc/ksp/pc/impls/ml/ml.cT422</a></div><div><br></div><div>and it should fail according to</div><div><br></div><div> <a href="https://bitbucket.org/petsc/petsc/src/643e5bfe5b452fa5bc89efaa4c603d713f2a6f29/src/sys/objects/pinit.c?at=master#cl-284">https://bitbucket.org/petsc/petsc/src/643e5bfe5b452fa5bc89efaa4c603d713f2a6f29/src/sys/objects/pinit.c?at=master#cl-284</a></div><div><br></div><div>Why don't the nightly tests fail?</div><div><br></div><div> Matt</div><div><br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex"><div class=""><div class="h5">
On Oct 1, 2014, at 7:03 AM, Chris Richardson <<a href="mailto:chris@bpi.cam.ac.uk">chris@bpi.cam.ac.uk</a>> wrote:<br>
<br>
> On 01/10/2014 11:33, Matthew Knepley wrote:<br>
>> On Wed, Oct 1, 2014 at 3:51 AM, Chris Richardson <<a href="mailto:chris@bpi.cam.ac.uk">chris@bpi.cam.ac.uk</a>><br>
>> wrote:<br>
>>> I have just run into this error after pulling the master branch of<br>
>>> petsc, when using the ML preconditioner in FEniCS.<br>
>>> It looks like a type error, but I guess FEniCS uses PETScInt, so<br>
>>> should be safe?<br>
>>> PETSC ERROR: Can only handle MPIU_REAL or MPIU_COMPLEX data types<br>
>> We need to see the entire error (with the stack).<br>
><br>
> OK, this kind of thing:-<br>
><br>
><br>
> [1]PETSC ERROR: Can only handle MPIU_REAL or MPIU_COMPLEX data types<br>
> ^C<br>
> Program received signal SIGINT, Interrupt.<br>
> 0x00007ffff64d9653 in epoll_wait () at ../sysdeps/unix/syscall-template.S:81<br>
> 81 ../sysdeps/unix/syscall-template.S: No such file or directory.<br>
> (gdb) up<br>
> #1 0x00007ffff72c8591 in ?? () from /usr/lib/libmpi.so.1<br>
> (gdb) up<br>
> #2 0x00007ffff72ca787 in opal_event_base_loop () from /usr/lib/libmpi.so.1<br>
> (gdb) up<br>
> #3 0x00007ffff72eda3e in opal_progress () from /usr/lib/libmpi.so.1<br>
> (gdb) up<br>
> #4 0x00007fffb42884d5 in ?? ()<br>
> from /usr/lib/openmpi/lib/openmpi/mca_grpcomm_bad.so<br>
> (gdb) up<br>
> #5 0x00007ffff723d02a in ompi_mpi_finalize () from /usr/lib/libmpi.so.1<br>
> (gdb) up<br>
> #6 0x00007ffff7766b12 in dolfin::SubSystemsManager::finalize_mpi ()<br>
> at /opt/packages/src/dolfin/dolfin/common/SubSystemsManager.cpp:249<br>
> 249 MPI_Finalize();<br>
> (gdb) up<br>
> #7 0x00007ffff7766cde in dolfin::SubSystemsManager::finalize ()<br>
> at /opt/packages/src/dolfin/dolfin/common/SubSystemsManager.cpp:219<br>
> 219 finalize_mpi();<br>
> (gdb) up<br>
> #8 0x00007ffff641a149 in __run_exit_handlers (status=1,<br>
> listp=0x7ffff679d6c8 <__exit_funcs>,<br>
> run_list_atexit=run_list_atexit@entry=true) at exit.c:82<br>
> 82 exit.c: No such file or directory.<br>
> (gdb) up<br>
> #9 0x00007ffff641a195 in __GI_exit (status=<optimised out>) at exit.c:104<br>
> 104 in exit.c<br>
> (gdb) up<br>
> #10 0x00007ffff729cc00 in orte_ess_base_app_abort () from /usr/lib/libmpi.so.1<br>
> (gdb) up<br>
> #11 0x00007ffff729c2a9 in orte_errmgr_base_error_abort ()<br>
> from /usr/lib/libmpi.so.1<br>
> (gdb) up<br>
> #12 0x00007ffff723bb69 in ompi_mpi_abort () from /usr/lib/libmpi.so.1<br>
> (gdb) up<br>
> #13 0x00007ffff37b9ee3 in PetscSum_Local (in=0x230f4520, out=0x7fffffffc650,<br>
> cnt=<optimised out>, datatype=0x7fffffffc428)<br>
> at /opt/packages/src/petsc/src/sys/objects/pinit.c:302<br>
> 302 MPI_Abort(MPI_COMM_WORLD,1);<br>
> (gdb) up<br>
> #14 0x00007fffb10dd4dc in mca_coll_basic_scan_intra ()<br>
> from /usr/lib/openmpi/lib/openmpi/mca_coll_basic.so<br>
> (gdb) up<br>
> #15 0x00007fffb08c7e19 in mca_coll_sync_scan ()<br>
> from /usr/lib/openmpi/lib/openmpi/mca_coll_sync.so<br>
> (gdb) up<br>
> #16 0x00007ffff725835d in PMPI_Scan () from /usr/lib/libmpi.so.1<br>
> (gdb) up<br>
> #17 0x00007ffff413ec45 in MatWrapML_MPIAIJ (newmat=0x16a39228,<br>
> reuse=MAT_INITIAL_MATRIX, mlmat=0x7ed6090)<br>
> at /opt/packages/src/petsc/src/ksp/pc/impls/ml/ml.c:422<br>
> 422 ierr = MPI_Scan(&m,&rstart,1,MPIU_INT,MPIU_SUM,mlmat->comm->USR_com);CHKERRQ(ierr);<br>
> (gdb) list<br>
> 417 ierr = MatSetSizes(A,m,n,PETSC_DECIDE,PETSC_DECIDE);CHKERRQ(ierr);<br>
> 418 ierr = MatSetType(A,MATMPIAIJ);CHKERRQ(ierr);<br>
> 419 /* keep track of block size for A matrices */<br>
> 420 ierr = MatSetBlockSize (A,mlmat->num_PDEs);CHKERRQ(ierr);<br>
> 421 ierr = PetscMalloc3(m,&nnzA,m,&nnzB,m,&nnz);CHKERRQ(ierr);<br>
> 422 ierr = MPI_Scan(&m,&rstart,1,MPIU_INT,MPIU_SUM,mlmat->comm->USR_com);CHKERRQ(ierr);<br>
> 423 rstart -= m;<br>
> 424<br>
> 425 for (i=0; i<m; i++) {<br>
> 426 row = gordering[i] - rstart;<br>
> (gdb)<br>
<br>
</div></div></blockquote></div><br><br clear="all"><div><br></div>-- <br>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>