[slurm-users] How to configure slurm not queuing the jobs?

2020-10-12 Thread Chaofeng Zhang
If there is no available resource when I submitting a job, I want slurm to return job submission failed directly. How to configure slurm? Thanks

Re: [slurm-users] Segfault with 32 processes, OK with 30 ???

2020-10-12 Thread Chris Samuel
On Monday, 12 October 2020 2:43:36 AM PDT Diego Zuccato wrote: > Seems so: > "The application appears to have been direct launched using "srun", > but OMPI was not built with SLURM's PMI support and therefore cannot > execute." > > So it seems I can't use srun to launch OpenMPI jobs. OK, I suspe

Re: [slurm-users] sbatch overallocation

2020-10-12 Thread Diego Zuccato
Il 10/10/20 18:53, Renfro, Michael ha scritto: > * Do you want to ensure that one job requesting 9 tasks (and 1 CPU per > task) can’t overstep its reservation and take resources away from > other jobs on those nodes? Cgroups [1] should be able to confine the > job to its 9 CPUs, and

Re: [slurm-users] Segfault with 32 processes, OK with 30 ???

2020-10-12 Thread Diego Zuccato
Il 08/10/20 08:48, Chris Samuel ha scritto: Sorry for being so late. I've had to wait for the node to be free. > Launch it with "srun" rather than "mpirun", that way it'll be managed by > Slurm. If your test program then says every rank is rank 0 that will tell > you > OpenMPI is not built wi

Re: [slurm-users] unable to run on all the logical cores

2020-10-12 Thread Diego Zuccato
Il 12/10/20 05:55, William Brown ha scritto: > We always disable hyper-threading on the compute nodes, at the > recommendation of the company that installed it, who reported that it > ran faster that way.  Multi-threading has a cost and is not ideal for > compute workloads.  It is better for thing