<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">Hi Junchao,<div class=""><br class=""></div><div class="">We have tried your two suggestions but the problem remains.</div><div class="">And the problem seems to be on the MPI_Isend line 117 in PetscGatherMessageLengths and not MPI_AllReduce.</div><div class=""><br class=""></div><div class="">We have now tried Intel MPI, Mpich, and OpenMPI, and so are thinking the problem must be elsewhere and not MPI.</div><div class=""><br class=""></div><div class="">Give that this is a 64 bit indices build of PETSc, is there some possible incompatibility between PETSc and MPI calls?</div><div class=""><br class=""></div><div class="">We are open to any other possible suggestions to try as other than valgrind on thousands of processes we seem to have run out of ideas.</div><div class=""><br class=""></div><div class="">Thanks, Randy M.</div><div class=""><br class=""></div><div class=""><div><blockquote type="cite" class=""><div class="">On Apr 13, 2020, at 8:54 AM, Junchao Zhang <<a href="mailto:junchao.zhang@gmail.com" class="">junchao.zhang@gmail.com</a>> wrote:</div><br class="Apple-interchange-newline"><div class=""><div dir="ltr" class=""><div dir="ltr" class=""><br clear="all" class=""><div class=""><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr" class="">--Junchao Zhang</div></div></div><br class=""></div><br class=""><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Mon, Apr 13, 2020 at 10:53 AM Junchao Zhang <<a href="mailto:junchao.zhang@gmail.com" class="">junchao.zhang@gmail.com</a>> wrote:<br class=""></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr" class=""><div class="">Randy,</div><div class=""> Someone reported similar problem before. It turned out an Intel MPI MPI_Allreduce bug. A workaround is setting the environment variable I_MPI_ADJUST_ALLREDUCE=1.arr</div></div></blockquote><div class=""> Correct: I_MPI_ADJUST_ALLREDUCE=1</div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr" class=""><div class=""> But you mentioned mpich also had the error. So maybe the problem is not the same. So let's try the workaround first. If it doesn't work, add another petsc option -build_twosided allreduce, which is a workaround for Intel MPI_Ibarrier bugs we met.</div> Thanks.<br clear="all" class=""><div class=""><div dir="ltr" class=""><div dir="ltr" class="">--Junchao Zhang</div></div></div><br class=""></div><br class=""><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Mon, Apr 13, 2020 at 10:38 AM Randall Mackie <<a href="mailto:rlmackie862@gmail.com" target="_blank" class="">rlmackie862@gmail.com</a>> wrote:<br class=""></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div class="">Dear PETSc users,<div class=""><br class=""></div><div class="">We are trying to understand an issue that has come up in running our code on a large cloud cluster with a large number of processes and subcomms.</div><div class="">This is code that we use daily on multiple clusters without problems, and that runs valgrind clean for small test problems.</div><div class=""><br class=""></div><div class="">The run generates the following messages, but doesn’t crash, just seems to hang with all processes continuing to show activity:</div><div class=""><br class=""></div><div style="margin:0in 0in 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif" class=""><span style="font-size:10pt;font-family:Verdana,sans-serif;color:rgb(31,73,125)" class="">[492]PETSC ERROR: #1 PetscGatherMessageLengths() line 117 in /mnt/home/cgg/PETSc/petsc-3.12.4/src/sys/utils/mpimesg.c<u class=""></u><u class=""></u></span></div><div style="margin:0in 0in 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif" class=""><span style="font-size:10pt;font-family:Verdana,sans-serif;color:rgb(31,73,125)" class="">[492]PETSC ERROR: #2 VecScatterSetUp_SF() line 658 in /mnt/home/cgg/PETSc/petsc-3.12.4/src/vec/vscat/impls/sf/vscatsf.c<u class=""></u><u class=""></u></span></div><div style="margin:0in 0in 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif" class=""><span style="font-size:10pt;font-family:Verdana,sans-serif;color:rgb(31,73,125)" class="">[492]PETSC ERROR: #3 VecScatterSetUp() line 209 in /mnt/home/cgg/PETSc/petsc-3.12.4/src/vec/vscat/interface/vscatfce.c<u class=""></u><u class=""></u></span></div><div class=""><span style="color:rgb(31,73,125);font-family:Verdana,sans-serif;font-size:10pt" class="">[492]PETSC ERROR: #4 VecScatterCreate() line 282 in /mnt/home/cgg/PETSc/petsc-3.12.4/src/vec/vscat/interface/vscreate.c</span></div><div class=""><br class=""></div><div class=""><br class=""></div><div class="">Looking at line 117 in PetscGatherMessageLengths we find the offending statement is the MPI_Isend:</div><div class=""><br class=""></div><div style="margin:0in 0in 0.0001pt;font-size:12pt;font-family:"Times New Roman",serif" class=""><span style="color:rgb(31,73,125)" class=""> </span><u class=""></u><u class=""></u></div><div style="margin:0in 0in 0.0001pt;font-size:12pt;font-family:"Times New Roman",serif" class=""><span style="font-size:11pt;font-family:"Courier New";color:rgb(31,73,125)" class=""> /* Post the Isends with the message length-info */</span><u class=""></u><u class=""></u></div><div style="margin:0in 0in 0.0001pt;font-size:12pt;font-family:"Times New Roman",serif" class=""><span style="font-size:11pt;font-family:"Courier New";color:rgb(31,73,125)" class=""> for (i=0,j=0; i<size; ++i) {</span><u class=""></u><u class=""></u></div><div style="margin:0in 0in 0.0001pt;font-size:12pt;font-family:"Times New Roman",serif" class=""><span style="font-size:11pt;font-family:"Courier New";color:rgb(31,73,125)" class=""> if (ilengths[i]) {</span><u class=""></u><u class=""></u></div><div style="margin:0in 0in 0.0001pt;font-size:12pt;font-family:"Times New Roman",serif" class=""><span style="font-size:11pt;font-family:"Courier New";color:rgb(31,73,125)" class=""> ierr = MPI_Isend((void*)(ilengths+i),1,MPI_INT,i,tag,comm,s_waits+j);CHKERRQ(ierr);</span><u class=""></u><u class=""></u></div><div style="margin:0in 0in 0.0001pt;font-size:12pt;font-family:"Times New Roman",serif" class=""><span style="font-size:11pt;font-family:"Courier New";color:rgb(31,73,125)" class=""> j++;</span><u class=""></u><u class=""></u></div><div style="margin:0in 0in 0.0001pt;font-size:12pt;font-family:"Times New Roman",serif" class=""><span style="font-size:11pt;font-family:"Courier New";color:rgb(31,73,125)" class=""> }</span><u class=""></u><u class=""></u></div><div class=""><span style="color:rgb(31,73,125);font-family:"Courier New";font-size:11pt" class=""> }</span> </div><div class=""><br class=""></div><div class="">We have tried this with Intel MPI 2018, 2019, and mpich, all giving the same problem.</div><div class=""><br class=""></div><div class="">We suspect there is some limit being set on this cloud cluster on the number of file connections or something, but we don’t know.</div><div class=""><br class=""></div><div class="">Anyone have any ideas? We are sort of grasping for straws at this point.</div><div class=""><br class=""></div><div class="">Thanks, Randy M.</div></div></blockquote></div>
</blockquote></div></div>
</div></blockquote></div><br class=""></div></body></html>