On Wed, Aug 17, 2011 at 6:55 PM, Dominik Szczerba <span dir="ltr"><<a href="mailto:dominik@itis.ethz.ch">dominik@itis.ethz.ch</a>></span> wrote:<br><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
Hi,<br>
<br>
I am getting the following valgrind complaint:<br>
<br>
==27366== Syscall param writev(vector[...]) points to uninitialised byte(s)<br>
==27366== at 0x6B5E789: writev (writev.c:56)<br>
==27366== by 0x5081F8: MPIDU_Sock_writev (sock_immed.i:610)<br>
==27366== by 0x50A4E3: MPIDI_CH3_iSendv (ch3_isendv.c:84)<br>
==27366== by 0x4EE2F6: MPIDI_CH3_EagerContigIsend (ch3u_eager.c:509)<br>
==27366== by 0x4F0284: MPID_Isend (mpid_isend.c:118)<br>
==27366== by 0x4D7BCA: MPIC_Isend (helper_fns.c:210)<br>
==27366== by 0xEC3ECD: MPIR_Alltoall (alltoall.c:420)<br>
==27366== by 0xEC4730: PMPI_Alltoall (alltoall.c:685)<br>
==27366== by 0xE38B3D: SetUp__ (setup.c:122)<br>
==27366== by 0xE3938C: PartitionSmallGraph__ (weird.c:39)<br>
==27366== by 0xE36678: ParMETIS_V3_PartKway (kmetis.c:131)<br>
==27366== by 0x6A0004: MatPartitioningApply_Parmetis (pmetis.c:97)<br>
==27366== by 0x69C600: MatPartitioningApply (partition.c:236)<br>
==27366== by 0x519266: PetscSolver::LoadMesh(std::string const&)<br>
(PetscSolver.cxx:415)<br>
==27366== by 0x4C1801: CD3T10_BOX::CD3T10_BOX() (cd3t10mpi_main.cxx:64)<br>
==27366== by 0x4C1318: main (cd3t10mpi_main.cxx:673)<br>
==27366== Address 0xc635afc is 12 bytes inside a block of size 72 alloc'd<br>
==27366== at 0x4C28FAC: malloc (vg_replace_malloc.c:236)<br>
==27366== by 0xE4963A: GKmalloc__ (util.c:151)<br>
==27366== by 0xE44AB1: PreAllocateMemory__ (memory.c:38)<br>
==27366== by 0xE3655B: ParMETIS_V3_PartKway (kmetis.c:116)<br>
==27366== by 0x6A0004: MatPartitioningApply_Parmetis (pmetis.c:97)<br>
==27366== by 0x69C600: MatPartitioningApply (partition.c:236)<br>
==27366== by 0x519266: PetscSolver::LoadMesh(std::string const&)<br>
(PetscSolver.cxx:415)<br>
==27366== by 0x4C1801: CD3T10_BOX::CD3T10_BOX() (cd3t10mpi_main.cxx:64)<br>
==27366== by 0x4C1318: main (cd3t10mpi_main.cxx:673)<br>
<br>
<br>
A few lines around PetscSolver.cxx:415:<br>
<br>
<br>
MatPartitioning part;<br>
ierr = MatPartitioningCreate(PETSC_COMM_WORLD, &part); CHKERRQ(ierr);<br>
ierr = MatPartitioningSetAdjacency(part, adj); CHKERRQ(ierr);<br>
ierr = MatPartitioningSetNParts(part, np); CHKERRQ(ierr);<br>
ierr = MatPartitioningSetFromOptions(part); CHKERRQ(ierr);<br>
IS isTetAssignment;<br>
415 ierr = MatPartitioningApply(part, &isTetAssignment); CHKERRQ(ierr);<br>
ierr = MatPartitioningDestroy(part); CHKERRQ(ierr);<br>
ierr = PetscGetTime(&time1); CHKERRQ(ierr);<br>
<br>
<br>
<br>
I do not immediately see anything wrong. Is this a real error? Did I<br>
overlook anything?<br></blockquote><div><br></div><div>I think this is fine (its a common complaint of valgrind about MPICH).</div><div><br></div><div> Matt</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
Many thanks for any opinions.<br>
<font color="#888888"><br>
Dominik</font></blockquote></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<br>