<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Re: MPI Fatal error OFI EP enable failed in Intel® MPI Library</title>
    <link>https://community.intel.com/t5/Intel-MPI-Library/MPI-Fatal-error-OFI-EP-enable-failed/m-p/1622928#M11852</link>
    <description>&lt;P&gt;By setting those flags, there are a lot of debug output which also seemed to have stopped the&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;original OFI EP enable failed (ofi_init.c:2245:create_vni_context:Address already in use)&amp;nbsp;&lt;/SPAN&gt;&lt;SPAN&gt;error.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;I was running MPI many many times in succession one after another using a script. Maybe the "vni context address" was not released fast enough between runs but having all these debug output slowed things down enough for it to be released before the next mpiexec ... call?&amp;nbsp;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Is that possible?&amp;nbsp;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Tue, 13 Aug 2024 13:20:56 GMT</pubDate>
    <dc:creator>YaDev</dc:creator>
    <dc:date>2024-08-13T13:20:56Z</dc:date>
    <item>
      <title>MPI Fatal error OFI EP enable failed</title>
      <link>https://community.intel.com/t5/Intel-MPI-Library/MPI-Fatal-error-OFI-EP-enable-failed/m-p/1622656#M11850</link>
      <description>&lt;P&gt;Launching this on Fedora 40&lt;/P&gt;&lt;P&gt;mpiexec -machinefile mfile -configure cfile someprogram&lt;/P&gt;&lt;P&gt;I encountered sporadic error like this&lt;/P&gt;&lt;P&gt;Abort(1614735) on node 0 (rank 0 in comm 0): Fatal error in PMPI_Init: Unknown error class, error stack:&lt;BR /&gt;MPIR_Init_thread(192)........:&amp;nbsp;&lt;/P&gt;&lt;P&gt;MPID_Init(1665)..............:&lt;/P&gt;&lt;P&gt;MPIDI_OFI_mpi_init_hook(1665):&lt;/P&gt;&lt;P&gt;create_vni_context(2245).....: OFI EP enable failed (ofi_init.c:2245:create_vni_context:Address already in use)&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;This does not happen every time. If it happens and then I relaunch it and then it can run fine.&lt;/P&gt;&lt;P&gt;&amp;nbsp;Is there anyway to get rid of this problem permanently?&amp;nbsp;&lt;/P&gt;&lt;P&gt;What is this "Address already in use" error?&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I have already search through the discussions and none of them seem to apply directly.&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 12 Aug 2024 10:49:17 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-MPI-Library/MPI-Fatal-error-OFI-EP-enable-failed/m-p/1622656#M11850</guid>
      <dc:creator>YaDev</dc:creator>
      <dc:date>2024-08-12T10:49:17Z</dc:date>
    </item>
    <item>
      <title>Re: MPI Fatal error OFI EP enable failed</title>
      <link>https://community.intel.com/t5/Intel-MPI-Library/MPI-Fatal-error-OFI-EP-enable-failed/m-p/1622661#M11851</link>
      <description>&lt;P&gt;&lt;a href="https://community.intel.com/t5/user/viewprofilepage/user-id/372497"&gt;@YaDev&lt;/a&gt;&amp;nbsp;&lt;BR /&gt;Please provide at least your HW and SW environment and the output of I_MPI_DEBUG=10.&lt;BR /&gt;&lt;BR /&gt;If you can reproduce the failure, please add I_MPI_HYDRA_DEBUG=1 and I_MPI_DEBUG=120&lt;/P&gt;</description>
      <pubDate>Mon, 12 Aug 2024 11:16:37 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-MPI-Library/MPI-Fatal-error-OFI-EP-enable-failed/m-p/1622661#M11851</guid>
      <dc:creator>TobiasK</dc:creator>
      <dc:date>2024-08-12T11:16:37Z</dc:date>
    </item>
    <item>
      <title>Re: MPI Fatal error OFI EP enable failed</title>
      <link>https://community.intel.com/t5/Intel-MPI-Library/MPI-Fatal-error-OFI-EP-enable-failed/m-p/1622928#M11852</link>
      <description>&lt;P&gt;By setting those flags, there are a lot of debug output which also seemed to have stopped the&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;original OFI EP enable failed (ofi_init.c:2245:create_vni_context:Address already in use)&amp;nbsp;&lt;/SPAN&gt;&lt;SPAN&gt;error.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;I was running MPI many many times in succession one after another using a script. Maybe the "vni context address" was not released fast enough between runs but having all these debug output slowed things down enough for it to be released before the next mpiexec ... call?&amp;nbsp;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Is that possible?&amp;nbsp;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Tue, 13 Aug 2024 13:20:56 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-MPI-Library/MPI-Fatal-error-OFI-EP-enable-failed/m-p/1622928#M11852</guid>
      <dc:creator>YaDev</dc:creator>
      <dc:date>2024-08-13T13:20:56Z</dc:date>
    </item>
  </channel>
</rss>

