Hello fellow coders,
you might be interested in the DRMAA bindings for Perl6, which you can find
here:
https://github.com/scovit/Scheduler-DRMAA
It provides the full C language API, and on top of that I implemented a
quite expressive, easy and experimental high level API, you might want to
use it
Hello,
I am developing a Spank plugin which starts a process per node. This is a
privileged process that performs some irrelevant things.
We don't want the process to be closed at the end of the SLURMs job
execution, but seems that SLURM is closing this process after the job
completion. Do you kn
You could also use a simple epilog script to save the output of ‘scontrol show
job’ to a file/database.
M
--
Merlin Hartley
Computer Officer
MRC Mitochondrial Biology Unit
Cambridge, CB2 0XY
United Kingdom
> On 15 Oct 2017, at 20:49, Ryan Richholt wrote:
>
> Is there any way to get the job c
Hi,
after reading your message about if OMPI 1.8 supports PMIx, I have
compiled OMPI 3.0.0. I resume, againg, all what I have done:
1. First of all, I have compiled contrib "pmi" package allocate
inside SLURM 17.02.7 folder: cd contribs/pmi2 && make && make
install --
All of the calls are thread safe
On October 15, 2017 11:37:55 AM MDT, "Frank Ramirez, Alvaro"
wrote:
>Hi all,
>
>
>New user but long time user and plugin developer here.
>
>
>I am currently porting an automated set of virtualization triggers for
>slurm to c/c++.
>
>
>As virtualization steps can
> If, now, I submit with "sbatch --distribution=cyclic -N 2 -n 12
> ./test-new.sh", what I get is:
> Process 0 on clus01.hpc.local out of 12
> Process 1 on clus02.hpc.local out of 12
> Process 2 on clus01.hpc.local out of 12
> Process 3 on clus01.hpc.local out of 12
> Process 4 on clus01.hpc.loca
Thanks, that sounds like a good idea. A prolog script could also handle
this right? That way if the node crashes while the job is running, it would
still be saved.
On Mon, Oct 16, 2017 at 3:20 AM Merlin Hartley <
merlin-sl...@mrc-mbu.cam.ac.uk> wrote:
> You could also use a simple epilog script t
Hi,
I have a compute node (CN) that is not running slurmd and is not directly
managed by slurm but that I would like to use via slurm.
Very crudely speaking I imagine that I could use an existing slurmd and use a
spank plugin to rewrite the IP address of an allocation such that a task is
exe
If I run with "--ntasks-per-node=6", result is:
Process 0 on clus01.hpc.local out of 12
Process 1 on clus02.hpc.local out of 12
Process 2 on clus01.hpc.local out of 12
Process 3 on clus02.hpc.local out of 12
Process 4 on clus01.hpc.local out of 12
Process 5 on clu
