<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=Windows-1252">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; color: rgb(0, 0, 0); font-size: 16px; font-family: Arial, sans-serif;">
<div>
<div><br>
</div>
<div>On further investigation, I traced the problem to a linking error (for some reason, I must set LIBS=‘-lmpi’ when running configure with SGI MPT). I found the hint in the README.SGI file.</div>
<div><br>
</div>
<div>Sorry for the premature bug report.</div>
<div><br>
</div>
<div>Thanks,</div>
<div><br>
</div>
<div>-Eric</div>
<div><br>
</div>
<div>
<div>Eric M. Kemp (SSAI)
<div>NASA/GSFC </div>
<div>Mail Code: 606 </div>
<div>Greenbelt, MD 20771 </div>
<div>301.286.9768 </div>
<div><a href="eric.kemp@nasa.gov">eric.kemp@nasa.gov</a></div>
<div><a href="eric.kemp@ssaihq.com">eric.kemp@ssaihq.com</a><br>
</div>
</div>
<div><font face="Courier,Courier New"><span style="font-size:11pt"><br>
</span></font></div>
</div>
</div>
<div><br>
</div>
<span id="OLK_SRC_BODY_SECTION">
<div style="font-family:Lucida Grande; font-size:11pt; text-align:left; color:black; BORDER-BOTTOM: medium none; BORDER-LEFT: medium none; PADDING-BOTTOM: 0in; PADDING-LEFT: 0in; PADDING-RIGHT: 0in; BORDER-TOP: #b5c4df 1pt solid; BORDER-RIGHT: medium none; PADDING-TOP: 3pt">
<span style="font-weight:bold">From: </span><<a href="mailto:parallel-netcdf-bounces@lists.mcs.anl.gov">parallel-netcdf-bounces@lists.mcs.anl.gov</a>> on behalf of Eric Kemp <<a href="mailto:eric.kemp@nasa.gov">eric.kemp@nasa.gov</a>><br>
<span style="font-weight:bold">Date: </span>Monday, June 20, 2016 at 4:38 PM<br>
<span style="font-weight:bold">To: </span>"<a href="mailto:parallel-netcdf@mcs.anl.gov">parallel-netcdf@mcs.anl.gov</a>" <<a href="mailto:parallel-netcdf@mcs.anl.gov">parallel-netcdf@mcs.anl.gov</a>><br>
<span style="font-weight:bold">Subject: </span>Problem with testing PNETCDF 1.7.0<br>
</div>
<div><br>
</div>
<div>
<div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; color: rgb(0, 0, 0); font-size: 16px; font-family: Arial, sans-serif;">
<div><br>
</div>
<div>Dear PNETCDF developers:</div>
<div><br>
</div>
<div>I’m attempting to install PNETCDF 1.7.0 on a Linux cluster running SLES 11.3 and GPFS, using SGI MPT 2.12 and Intel 15.0.3.187 compilers. I get the following error when ‘make testing’ runs the tst_f90 program:</div>
<div><br>
</div>
<div>
<blockquote style="margin:0 0 0 40px; border:none; padding:0px;">
<div>mpiexec_mpt -n 1 ./tst_f90 ./testfile.nc</div>
<div>srun.slurm: cluster configuration lacks support for cpu binding</div>
<div>MPT ERROR: rank:0, function:MPI_TYPE_CREATE_HVECTOR, Invalid argument</div>
<div>MPT: Global rank 0 is aborting with error code 0.</div>
<div> Process ID: 17524, Host: borgo015, Program: /gpfsm/dnb32/emkemp/NUWRFLIB/svn/branches/features/external_upgrades/builds/parallel-netcdf-1.7.0/test/F90/tst_f90</div>
<div><br>
</div>
<div>MPT: --------stack traceback-------</div>
<div>
<div>MPT: Attaching to program: /proc/17524/exe, process 17524</div>
<div>MPT: Try: zypper install -C "debuginfo(build-id)=48172710254f4e2549684d7d3e9f9622272d6c66"</div>
<div>MPT: (no debugging symbols found)...done.</div>
<div>MPT: [Thread debugging using libthread_db enabled]</div>
<div>MPT: Using host libthread_db library "/lib64/libthread_db.so.1".</div>
<div>MPT: Try: zypper install -C "debuginfo(build-id)=f0721cb50ab9fbdf06314a53bff5af581bbefe64"</div>
<div>MPT: (no debugging symbols found)...done.</div>
<div>MPT: Try: zypper install -C "debuginfo(build-id)=e2cab3c95cb1189420734b4af264b047355be2e5"</div>
<div>MPT: (no debugging symbols found)...done.</div>
<div>MPT: Try: zypper install -C "debuginfo(build-id)=732292820e69f70459cb927ade5b49bc56d32b0f"</div>
<div>MPT: (no debugging symbols found)...done.</div>
<div>MPT: Try: zypper install -C "debuginfo(build-id)=9fdc592b21682a31f460f6f043f50eea8c8b6821"</div>
<div>MPT: (no debugging symbols found)...done.</div>
<div>MPT: Try: zypper install -C "debuginfo(build-id)=e1a13ecb56367b69b89d1c9ca1a4c42167336030"</div>
<div>MPT: (no debugging symbols found)...done.</div>
<div>MPT: Try: zypper install -C "debuginfo(build-id)=719375f80fd84b85b905db2c20ec70e8805b36e5"</div>
</div>
</blockquote>
</div>
<blockquote style="margin:0 0 0 40px; border:none; padding:0px;">
<div>
<div>MPT: (no debugging symbols found)...done.</div>
<div>MPT: Try: zypper install -C "debuginfo(build-id)=c4ce7f7c226abce4cec56fdbb4ed87e49024868d"</div>
<div>MPT: (no debugging symbols found)...done.</div>
<div>MPT: 0x00002aaaaacdc3bf in waitpid () from /lib64/libpthread.so.0</div>
<div>MPT: (gdb) #0 0x00002aaaaacdc3bf in waitpid () from /lib64/libpthread.so.0</div>
<div>MPT: #1 0x00002aaaab3e40ec in mpi_sgi_system (command=<optimized out>) at sig.c:99</div>
<div>MPT: #2 MPI_SGI_stacktraceback (header=<optimized out>) at sig.c:319</div>
<div>MPT: #3 0x00002aaaab337aea in print_traceback (ecode=0) at abort.c:197</div>
<div>MPT: #4 0x00002aaaab337bde in MPI_SGI_abort () at abort.c:85</div>
<div>MPT: #5 0x00002aaaab36f042 in errors_are_fatal (comm=<optimized out>, </div>
<div>MPT: code=<optimized out>) at errhandler.c:220</div>
<div>MPT: #6 0x00002aaaab36f2f1 in MPI_SGI_error (comm=1, code=13) at errhandler.c:56</div>
<div>MPT: #7 0x00002aaaab3edd1d in PMPI_Type_create_hindexed (count=0, blocklens=0x0, </div>
<div>MPT: indices=0x2872760, oldtype=27, newtype=0x7fffffff8a98)</div>
<div>MPT: at type_create_hindexed.c:25</div>
<div>MPT: #8 0x00000000006f40fc in fillerup_aggregate..0 ()</div>
</div>
</blockquote>
<div>
<blockquote style="margin:0 0 0 40px; border:none; padding:0px;">
<div>MPT: #9 0x00000000006ea9fb in ncmpii_NC_enddef ()</div>
<div>MPT: #10 0x00000000006eb349 in ncmpii_enddef ()</div>
<div>MPT: #11 0x00000000006dedef in ncmpi_enddef ()</div>
<div>MPT: #12 0x0000000000406877 in pnetcdf_mp_nf90mpi_enddef_ ()</div>
<div>MPT: #13 0x0000000000405173 in MAIN__ ()</div>
<div>MPT: #14 0x00000000004049ee in main ()</div>
<div>MPT: (gdb) A debugging session is active.</div>
<div>MPT: </div>
<div>MPT: Inferior 1 [process 17524] will be detached.</div>
<div>MPT: </div>
<div>MPT: Quit anyway? (y or n) [answered Y; input not from terminal]</div>
<div>MPT: Detaching from program: /proc/17524/exe, process 17524</div>
<div><br>
</div>
<div>MPT: -----stack traceback ends-----</div>
<div>slurmstepd-borgo015: *** STEP 8841377.772 CANCELLED AT 2016-06-20T16:18:33 *** on borgo015</div>
<div>srun.slurm: Job step aborted: Waiting up to 2 seconds for job step to finish.</div>
<div>srun.slurm: error: borgo015: task 0: Exited with exit code 255</div>
</blockquote>
</div>
<div><br>
</div>
<div>I’ve traced the trigger to the setting of the “_FillValue” attribute for the 3D pressure variable P in tst_f90.f90. If I change the attribute name to “FillValue” the test program runs w/o apparent error.</div>
<div><br>
</div>
<div>I have not found anything in the underlying PNetCDF Fortran or C codes that would explain this. Do you have any suggestions?</div>
<div><br>
</div>
<div>Thanks,</div>
<div><br>
</div>
<div>-Eric</div>
<div><br>
</div>
<div>
<div>Eric M. Kemp (SSAI)
<div>NASA/GSFC </div>
<div>Mail Code: 606 </div>
<div>Greenbelt, MD 20771 </div>
<div>301.286.9768 </div>
<div><a href="eric.kemp@nasa.gov">eric.kemp@nasa.gov</a></div>
<div><a href="eric.kemp@ssaihq.com">eric.kemp@ssaihq.com</a><br>
</div>
</div>
<div><font face="Courier,Courier New"><span style="font-size:11pt"><br>
</span></font></div>
</div>
</div>
</div>
</span>
</body>
</html>