Re: [OMPI users] Need help running jobs across different IB vendors

2013-10-15 Thread Kevin M. Hildebrand
s] Need help running jobs across different IB vendors "Kevin M. Hildebrand" writes: > Hi, I'm trying to run an OpenMPI 1.6.5 job across a set of nodes, some > with Mellanox cards and some with Qlogic cards. Maybe you shouldn't... (I'm blessed in one cluster with

Re: [OMPI users] Need help running jobs across different IB vendors

2013-10-14 Thread Kevin M. Hildebrand
f Squyres (jsquyres)" 1. Can you verify that you're running the same version/build of Open MPI on all three machines (mpirun machine, g18-6, and g17-33)? 2. Can you mpirun non-MPI programs, like hostname? On Oct 10, 2013, at 8:41 AM, Kevin M. Hildebrand wrote: > Hi, I'm tryi

[OMPI users] Need help running jobs across different IB vendors

2013-10-10 Thread Kevin M. Hildebrand
Hi, I'm trying to run an OpenMPI 1.6.5 job across a set of nodes, some with Mellanox cards and some with Qlogic cards. I'm getting errors indicating "At least one pair of MPI processes are unable to reach each other for MPI communications". As far as I can tell all of the nodes are properly co

[OMPI users] Unterminated log buffer causes corrupt log messages

2013-10-09 Thread Kevin M. Hildebrand
Hi, I just noticed a bug in the common logging code in both 1.6.5 and 1.7.2. For sites with hostnames longer than 32 characters, the terminating NULL is getting cut off the hostname string. Here's a simple patch to fix: diff -c -r1.1 opal/util/output.c *** opal/util/output.c 2013/10/09 14:09: