[slurm-users] Job not running of the specified node

[Marcus Wagner]

Hi mahmood,

yes that is totally normal.

please use sbatch instead of salloc.

If you use salloc, you just create an allocation. You would normally 
srun to that allocation.

To be clear, salloc does not create a batchjob, which gets executed on 
the remote host. After salloc returns (which might take a while, if your 
cluster is full), you are still on the login node, but have a 
"reservation" for the asked resources.
You will see, that your environment is "poisened" with additional env 
variables. So, I would strongly recommend to use different terminals, if 
you would like to have parallel allocations opened by salloc. srun would 
then use these env variables to get onto the right node (if I remember 
right).

What you want to do, is create a batchscript, submit it to the 
scheduler, such that the jobs gets executed on the host as soon as there 
are free resources.
This is done via "sbatch run.sh", not salloc run.sh.


Best
Marcus

On 7/9/19 9:46 AM, Mahmood Naderan wrote:
> Hi,
> I use the following script for qemu run
>
> #!/bin/bash
> #SBATCH --nodelist=compute-0-1
> #SBATCH --cores=8
> #SBATCH --mem=40G
> #SBATCH --partition=QEMU
> #SBATCH --account=q20_8
>
> USERN=`whoami`
> qemu-system-x86_64 -m 40000 -smp cores=8 -hda win7_sp1_x64.img -boot c 
> -usbdevice tablet -enable-kvm -device e1000,netdev=host_files -netdev 
> user,net=10.0.2.0/24,id=host_files <http://10.0.2.0/24,id=host_files>
>
> Although I have specified "compute-0-1", when I run "salloc ./run.sh", 
> it puts the job on the frontend.
>
> Is that normal? If there is any problem with the node I have 
> specified, then I should receive an error or waiting message. Isn't that?
>
>
> Regards,
> Mahmood
>
>

-- 
Marcus Wagner, Dipl.-Inf.

IT Center
Abteilung: Systeme und Betrieb
RWTH Aachen University
Seffenter Weg 23
52074 Aachen
Tel: +49 241 80-24383
Fax: +49 241 80-624383
wagner at itc.rwth-aachen.de
www.itc.rwth-aachen.de

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.schedmd.com/pipermail/slurm-users/attachments/20190709/dfd62de8/attachment.htm>