From fdb159e35504c02790367bbb807684fb0dd1960c Mon Sep 17 00:00:00 2001 From: Morris Jette <jette@schedmd.com> Date: Tue, 23 Jun 2015 08:47:08 -0700 Subject: [PATCH] Add note about OpenMPI locked memory limit failure --- doc/html/mpi_guide.shtml | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/doc/html/mpi_guide.shtml b/doc/html/mpi_guide.shtml index 07a96982b81..23fc5fcc459 100644 --- a/doc/html/mpi_guide.shtml +++ b/doc/html/mpi_guide.shtml @@ -98,7 +98,6 @@ $ salloc -n4 sh # allocates 4 processors and spawns shell for job > srun --mpi=pmi2 -n 4 a.out </pre> - <p>If the ports reserved for a job step are found by the Open MPI library to be in use, a message of this form will be printed and the job step will be re-launched:<br> @@ -108,6 +107,12 @@ Repeated failures should be reported to your system administrator in order to rectify the problem by cancelling the processes holding those ports.</p> +<p>NOTE: Some kernels and system configurations have resulted in a locked memory +too small for proper OpemMPI functionality, resulting in application failure +with a segmentation fault. This may be fixed by configuring the slurmd daemon +to execute with a larger limit. For example, add "LimitMEMLOCK=infinity" to +your slurmd.service file.</p> + <hr size=4 width="100%"> <h2><a name="intel_mpi"><b>Intel MPI</b></a></h2> @@ -512,6 +517,6 @@ $ srun -N4 -n16 a.out <hr size=4 width="100%"> -<p style="text-align:center;">Last modified 20 April 2015</p> +<p style="text-align:center;">Last modified 23 June 2015</p> <!--#include virtual="footer.txt"--> -- GitLab