Intel® Cluster Ready

Intel MPI Library Troubleshooting Guide

The latest versions of the Intel MPI Library User's Guides have added an expanded Troubleshooting section.  It provides the following information:

  • General Intel MPI Library troubleshooting practices
  • Typical MPI failures with corresponding output messages and behavior when a failure occurs
  • Recommendations on potential root causes and solutions

Here are direct links to these new sections:

How to use the Intel® Cluster Checker v3 SDK with gcc5

When compiling connector extensions in the Intel® Cluster Checker v3 SDK it is recommended to use an Intel compiler version 15.0 or newer and a gcc/g++ compiler version 4.9.0 or newer, as described in the Intel® Cluster Checker developer's Guide. This explicitly includes gcc version 5.1.0 and newer as well.

  • Parceiros
  • Linux*
  • Servidor
  • Intel® Cluster Checker
  • Intel Cluster Ready
  • Intel Cluster Checker
  • Intel Cluster Checker v3
  • Intel Cluster Checker v3.0
  • Cluster Checker
  • Intel® Cluster Ready
  • Computação de cluster
  • Bizarre authenticity of host issue when running across multiple nodes with Intel MPI

    I am attempting to run a job across three nodes.  I have configured passwordless ssh and it definitely works in between every node (each node can ssh to the other two without a password).  The known_hosts file is definitely correct and all 3 nodes have identical .ssh directories.  I have also tried adding the keys to ssh-agent, although I'm not sure if that was necessary either as I didn't specify a pass phrase when generating the id_rsa key (I know this is terrible security but it's temporary for the sake of testing).

    How to use the Intel® Cluster Checker v3 SDK on a cluster using multiple Linux Distributions

    Linux based HPC clusters can use different Linux distributions or different versions of a given Linux distribution for different types of nodes in the HPC cluster.

    When the Linux distribution on which the connector extension has been built uses a glibc version 2.14 or newer and the Linux distribution where the connector extension is used, i.e. where clck-analyze is executed, uses a glibc version lower than 2.14, clck-analyze is not able to execute the shared library of the connector extension due to a missing symbol.

    clck-analyze will show a message like this:

  • Parceiros
  • Linux*
  • Servidor
  • Intel® Cluster Checker
  • Intel Cluster Ready
  • Intel Cluster Checker
  • Intel Cluster Checker v3
  • Intel Cluster Checker v3.0
  • Cluster Checker
  • Intel® Cluster Ready
  • Computação de cluster
  • Computação paralela
  • Unable to launch MPI on Windows 2012

    I have been using Intel MPI library on a Windows 2008 R1 server for few years without any issues. However, we recently switched to Windows Server 2012 R2, and now I can't launch MPI due to following error, when I use the command line -

    mpiexec -n 1 -localroot  ./eDR_IMC.exe

    " Error while connecting to host, No connection could be made because the target machine actively refused it. (10061)
    Connect on sock (host=eDR-IMC2, port=8676) failed, exhaused all end points
    Unable to connect to 'eDR-IMC2:8676',
    sock error: Error = -1"

    MPI command question

    Dear all,

    I use MPI to run program for the given work path. The program works when I run the following command:

    mpiexec -wdir "Z:\test" -host 1 n01 1 z:\fem

    However, when running the following command:

    mpiexec -wdir "Z:\test" -n 1 z:\fem

    The program displayed the following error:

    forrtl: severe (29): file not found, unit 1, file C:\Windows\system32\parainfo\control.dat

    The 'control.dat' is placed at z:\test\parainfo, and the program will search for 'control.dat' from 'parainfo' automatically.

    Is it possible to us Intel MPI 5.1.0.038 with TCP over ethernet?

    I have just installed Intel 5.1.0.038 into a shared NFS space meant for use by my team who share four machines connected by Ethernet.  I have a machines.LINIX file listing the hostname of each machine that I saved into the NFS space.  My intention is for us to use the library over the Ethernet connection, but I am not sure that I have configured it correctly to do this.  I am not the administrator of the machines and so I do not have explicit root access.  However, I am in the sudoer group.  During the installation, I was not able to install using the "Run using sudo privileges and password

    To Intel: How to run Phi 5110p with host and Cluster Studio under Windows?

    Hi,

    I bought a Phi 5110p and Cluster Studio under Windows in an Intel campaign in order to use MPI to feed the Phi card. Hardwarewise I understand the major issues but softwarewise it is still unclear to me what the right way forward is, Can I work with W7 or should I use some other Windows product? The reason for clinging to Windows is that I have a lot of QuckWin based graphics that keep me informed what is going on during the computations.

    Best regards

    Anders S

    Where is uninstall.sh file in the MPI 5.1 distribution?

    I installed MPI 5.1.0.38 on July 16 this year, but I did not install it correctly.  I want to uninstall it, but I can't find the uninstall.sh script referenced in the Intel® MPI Library for Linux* OS Installation Guide: "To uninstall the Intel® MPI Library, go to the Intel MPI Library installation directory and run the
    uninstall. sh script."  I am not sure how to uninstall the software without the script. I will appreciate any assistance in helping me find this script.

    Thank you,

    Rashawn Knapp

     

     

    Assine o Intel® Cluster Ready