[slurm-dev] Re: Intel MPI Performance inconsistency (and workaround)

2014-08-25 Thread Andy Riebs
Assuming this is a Gnu/Linux system, be sure that you have /etc/sysconfig/slurm on all nodes with the line ulimit -l unlimited That can account for differences in processing between system startup and subsequently restarting the daemons by hand. Andy On 08/21/2014 02:42 PM, Jesse Stroik w

[slurm-dev] Re: Error: Unable to contact slurm controller

2014-08-25 Thread Jeff Falgout
On Wed, Aug 20, 2014 at 3:39 PM, Gerry Creager - NOAA Affiliate < gerry.crea...@noaa.gov> wrote: > Hi, Trey > > That's what I am intuiting, as well, but: > > gerry@loki:~/software/wrf/NME/DART_Lanai/models/wrf/work> egrep > '^(PartitionName|NodeName)' /opt/slurm/default/etc/slurm.conf > NodeName=

[slurm-dev] Re: unable to start slurmdbd service

2014-08-25 Thread Christopher B Coffey
Hi Izimiyati, Do you have: /usr/lib64/slurm/accounting_storage_mysql.so Installed on the build host? It looks like you may have been trying to put it in /opt/slurm however. Your Slurm configure statement if used as is, may have had issues as there are erroneous spaces placed by “—sysconfdir”,

[slurm-dev] Bug in displaying nodes for pending jobs with multiple CPUs per task

2014-08-25 Thread Jesse Stroik
We noticed an inconsistency when slurm has pending jobs in the number of expected nodes it will use. My understanding is that the number should be calculated based on the maximum node size (by cpu) and the number of CPUs a job needs. A quick and dirty review of the code makes it look like it

[slurm-dev] Re: Intel MPI Performance inconsistency (and workaround)

2014-08-25 Thread Jesse Stroik
I performed some testing on this today with a set of freshly imaged nodes and it appears to have worked. Thanks, Andy. Best, Jesse On 8/25/2014 8:24 AM, Andy Riebs wrote: Assuming this is a Gnu/Linux system, be sure that you have /etc/sysconfig/slurm on all nodes with the line ulimit -l u