[OMPI users] Error: "all nodes which are allocated for this job are already filled"

Hi, We have been trying to run MPI jobs (consisting of two different binaries, one each ) in two nodes, using hostfile option as following mpirun --allow-run-as-root --mca pml yalla -n 1 --hostfile /root/host1 /root/app2 : -n 1 --hostfile /root/host2 /root/backend We are doing this in chroot en

Re: [OMPI users] performance issue mpi_init

On Apr 28 [07:57], Ralph Castain wrote: > Here is what I get on my CentOS7 system using the 1.8.5 about to be released: I have now tried 1.8.5 release candidate 3 and now I get much better performance. So, I will just move on to 1.8.5 and consider this solved. > If you have a hostfile (or allocat

Re: [OMPI users] Error: "all nodes which are allocated for this job are already filled"

Try adding —mca ras_base_verbose 10 to your cmd line and let’s see what it thinks it is doing. Which OMPI version are you using - master? > On May 6, 2015, at 11:24 PM, Rahul Yadav wrote: > > Hi, > > We have been trying to run MPI jobs (consisting of two different binaries, > one each ) in t

[OMPI users] How does mpirun handle Ctrl+C?

Hello, How does mpirun or mpiexec handle Ctrl+C? I noticed when I use Ctrl+C on a running python script (without MPI), this generates a KeyboardInterrupt exception which I can catch and do something with, but when I use mpirun to run the python script, so far as I can tell, no exception is generate

Re: [OMPI users] How does mpirun handle Ctrl+C?

When mpirun receives a Ctrl-C, it hits each of its processes with a SIGTERM, followed a little later by SIGKILL if the proc didn’t terminate. > On May 7, 2015, at 2:31 PM, Seth Axen wrote: > > Hello, > How does mpirun or mpiexec handle Ctrl+C? I noticed when I use Ctrl+C on a > running python