<div dir="ltr">Thanks for your quick responses!<div><br></div><div>Attached is the configure.log obtained without using the --with-batch option. Configures without errors but fails at the 'make test' stage. A snippet of the output with the error (which I attributed to the job manager) is:</div><div><br></div><div><br></div><div><br></div><div>> Local host: hpca-login<br></div><div>> Registerable memory: 32768 MiB</div><div>> Total memory: 65427 MiB</div><div>> </div><div>> Your MPI job will continue, but may be behave poorly and/or hang.</div><div>> --------------------------------------------------------------------------</div><div>3c25</div><div>< 0 KSP Residual norm 0.239155 </div><div>---</div><div>> 0 KSP Residual norm 0.235858 </div><div>6c28</div><div>< 0 KSP Residual norm 6.81968e-05 </div><div>---</div><div>> 0 KSP Residual norm 2.30906e-05 </div><div>9a32,33</div><div>> [hpca-login:38557] 1 more process has sent help message help-mpi-btl-openib.txt / reg mem limit low</div><div>> [hpca-login:38557] Set MCA parameter "orte_base_help_aggregate" to 0 to see all help / error messages</div><div>/home/trianas/petsc-3.8.3/src/snes/examples/tutorials</div><div>Possible problem with ex19_fieldsplit_fieldsplit_mumps, diffs above</div><div>=========================================</div><div>Possible error running Fortran example src/snes/examples/tutorials/ex5f with 1 MPI process</div><div>See <a href="http://www.mcs.anl.gov/petsc/documentation/faq.html">http://www.mcs.anl.gov/petsc/documentation/faq.html</a></div><div>--------------------------------------------------------------------------</div><div>WARNING: It appears that your OpenFabrics subsystem is configured to only</div><div>allow registering part of your physical memory. This can cause MPI jobs to</div><div>run with erratic performance, hang, and/or crash.</div><div><br></div><div>This may be caused by your OpenFabrics vendor limiting the amount of</div><div>physical memory that can be registered. You should investigate the</div><div>relevant Linux kernel module parameters that control how much physical</div><div>memory can be registered, and increase them to allow registering all</div><div>physical memory on your machine.</div><div><br></div><div>See this Open MPI FAQ item for more information on these Linux kernel module</div><div>parameters:</div><div><br></div><div> <a href="http://www.open-mpi.org/faq/?category=openfabrics#ib-locked-pages">http://www.open-mpi.org/faq/?category=openfabrics#ib-locked-pages</a></div><div><br></div><div> Local host: hpca-login</div><div> Registerable memory: 32768 MiB</div><div> Total memory: 65427 MiB</div><div><br></div><div>Your MPI job will continue, but may be behave poorly and/or hang.</div><div>--------------------------------------------------------------------------</div><div>Number of SNES iterations = 4</div><div>Completed test examples</div><div>=========================================</div><div>Now to evaluate the computer systems you plan use - do:</div><div>make PETSC_DIR=/home/trianas/petsc-3.8.3 PETSC_ARCH=arch-linux2-c-debug streams</div><div><br></div><div><br></div><div><br></div></div><div class="gmail_extra"><br><div class="gmail_quote">On Sun, Dec 17, 2017 at 11:32 PM, Matthew Knepley <span dir="ltr"><<a href="mailto:knepley@gmail.com" target="_blank">knepley@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div class="gmail_extra"><div class="gmail_quote"><span class="">On Sun, Dec 17, 2017 at 3:29 PM, Santiago Andres Triana <span dir="ltr"><<a href="mailto:repepo@gmail.com" target="_blank">repepo@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div class="gmail_extra">Dear petsc-users,</div><div class="gmail_extra"><br></div><div class="gmail_extra">I'm trying to install petsc in a cluster that uses a job manager. This is the configure command I use:</div><div class="gmail_extra"><br></div><div class="gmail_extra">./configure --known-mpi-shared-libraries=1 --with-scalar-type=complex --with-mumps=1 --download-mumps --download-parmetis --with-blaslapack-dir=/sw/sdev<wbr>/intel/psxe2015u3/composer_xe_<wbr>2015.3.187/mkl --download-metis --with-scalapack=1 --download-scalapack --with-batch<br></div><div class="gmail_extra"><br></div><div class="gmail_extra">This fails when including the option --with-batch together with --download-scalapack:</div></div></blockquote><div><br></div></span><div>We need configure.log</div><span class=""><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div class="gmail_extra"><div class="gmail_extra">==============================<wbr>==============================<wbr>===================</div><div class="gmail_extra"> Configuring PETSc to compile on your system </div><div class="gmail_extra">==============================<wbr>==============================<wbr>===================</div><div class="gmail_extra">TESTING: check from config.libraries(config/BuildS<wbr>ystem/config/libraries.py:158)<wbr> *****************************<wbr>******************************<wbr>********************</div><div class="gmail_extra"> UNABLE to CONFIGURE with GIVEN OPTIONS (see configure.log for details):</div><div class="gmail_extra">------------------------------<wbr>------------------------------<wbr>-------------------</div><div class="gmail_extra">Unable to find scalapack in default locations!</div><div class="gmail_extra">Perhaps you can specify with --with-scalapack-dir=<director<wbr>y></div><div class="gmail_extra">If you do not want scalapack, then give --with-scalapack=0</div><div class="gmail_extra">You might also consider using --download-scalapack instead</div><div class="gmail_extra">******************************<wbr>******************************<wbr>*******************</div><div class="gmail_extra"><br></div><div class="gmail_extra"><br></div></div><div class="gmail_extra">However, if I omit the --with-batch option, the configure script manages to succeed (it downloads and compiles scalapack; the install fails later at the make debug because of the job manager).</div></div></blockquote><div><br></div></span><div>Can you send this failure as well?</div><div><br></div><div> Thanks,</div><div><br></div><div> Matt</div><span class=""><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div class="gmail_extra"> Any help or suggestion is highly appreciated. Thanks in advance!</div><span class="m_7862465139904345124HOEnZb"><font color="#888888"><div class="gmail_extra"><br></div><div class="gmail_extra">Andres </div></font></span></div>
</blockquote></span></div><span class="HOEnZb"><font color="#888888"><br><br clear="all"><div><br></div>-- <br><div class="m_7862465139904345124gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div>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><br></div><div><a href="http://www.caam.rice.edu/~mk51/" target="_blank">https://www.cse.buffalo.edu/~<wbr>knepley/</a><br></div></div></div></div></div>
</font></span></div></div>
</blockquote></div><br></div>