<?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 MPI over mmaped region kills Kernel? in Intel® MPI Library</title>
    <link>https://community.intel.com/t5/Intel-MPI-Library/MPI-over-mmaped-region-kills-Kernel/m-p/1075565#M4759</link>
    <description>&lt;P&gt;Hi,&lt;/P&gt;

&lt;P&gt;I use MPI (with Infiniband's RDMA enabled) over mmaped region. The size of mmap region is larger than the physical memory size, so I expect TLB is updated often, which may incur 'undefined' behavior of Infiniband's RDMA. The application kills the kernel (kernel panic),&lt;SPAN style="font-size: 1em; line-height: 1.5;"&gt;&amp;nbsp;which is absolutely not acceptible (User application code never incur it)&lt;/SPAN&gt;&lt;/P&gt;

&lt;P&gt;I suspect Infiniband's RDMA capability which bypasses translation buffer of CPU and accesses physical memory directly as one of the reasons for corrupting OS 'somehow'.&lt;/P&gt;

&lt;P&gt;&amp;nbsp;1. Can RDMA capability occur such a problem I described?&lt;/P&gt;

&lt;P&gt;&amp;nbsp;2. I tried with 'I_MPI_DAPL_TRANSLATION_CACHE' disabled, but the issue is not resolved. (I don't see any message saying 'I_MPI_DAPL_TRANSALCTION_CACHE=0' even with 'I_MPI_DEBUG=100', am I miss-using the env. vars?)&lt;/P&gt;

&lt;P&gt;many thanks for all :D&lt;/P&gt;</description>
    <pubDate>Wed, 17 Feb 2016 05:30:15 GMT</pubDate>
    <dc:creator>seongyun_k_</dc:creator>
    <dc:date>2016-02-17T05:30:15Z</dc:date>
    <item>
      <title>MPI over mmaped region kills Kernel?</title>
      <link>https://community.intel.com/t5/Intel-MPI-Library/MPI-over-mmaped-region-kills-Kernel/m-p/1075565#M4759</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;

&lt;P&gt;I use MPI (with Infiniband's RDMA enabled) over mmaped region. The size of mmap region is larger than the physical memory size, so I expect TLB is updated often, which may incur 'undefined' behavior of Infiniband's RDMA. The application kills the kernel (kernel panic),&lt;SPAN style="font-size: 1em; line-height: 1.5;"&gt;&amp;nbsp;which is absolutely not acceptible (User application code never incur it)&lt;/SPAN&gt;&lt;/P&gt;

&lt;P&gt;I suspect Infiniband's RDMA capability which bypasses translation buffer of CPU and accesses physical memory directly as one of the reasons for corrupting OS 'somehow'.&lt;/P&gt;

&lt;P&gt;&amp;nbsp;1. Can RDMA capability occur such a problem I described?&lt;/P&gt;

&lt;P&gt;&amp;nbsp;2. I tried with 'I_MPI_DAPL_TRANSLATION_CACHE' disabled, but the issue is not resolved. (I don't see any message saying 'I_MPI_DAPL_TRANSALCTION_CACHE=0' even with 'I_MPI_DEBUG=100', am I miss-using the env. vars?)&lt;/P&gt;

&lt;P&gt;many thanks for all :D&lt;/P&gt;</description>
      <pubDate>Wed, 17 Feb 2016 05:30:15 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-MPI-Library/MPI-over-mmaped-region-kills-Kernel/m-p/1075565#M4759</guid>
      <dc:creator>seongyun_k_</dc:creator>
      <dc:date>2016-02-17T05:30:15Z</dc:date>
    </item>
  </channel>
</rss>

