Hi Sid,
On our cluster, it performs just like your PBS cluster.
$ srun -N 1 --cpus-per-task 8 --time 01:00:00 --mem 2g --partition physicaltest
-q hpcadmin --pty python3
srun: job 27060036 queued and waiting for resources
srun: job 27060036 has been allocated resources
Python 3.6.8 (default, Aug
G'Day all,
I've had a question from a user of our new HPC, the following should
explain it:
➜ srun -N 1 --cpus-per-task 8 --time 01:00:00 --mem 2g --pty python3
Python 3.6.8 (default, Nov 16 2020, 16:55:22)
[GCC 4.8.5 20150623 (Red Hat 4.8.5-44)] on linux
Type "help", "copyright", "credits" or "l
Hi:
If you (Shaohao) mean you want to limit all running jobs to the sum of
up to N non-array-jobs and up to M array jobs, could you have N
"local" licenses of LicenseName 'nonarray' (e.g.) and M "local"
licenses of LicenseName 'array', and cause job_submit lua to add a
request for a license of the
You can specify a partition priority in the partition line in slurm.conf,
e.g. Priority=65000 (I forget what the max is...)
On Thu, Jun 17, 2021 at 10:31 PM wrote:
> Thanks for the help. We tried to reduce the sched_interval and the pending
> time decreased as expected.
>
> But the influence of
Thanks for the help. We tried to reduce the sched_interval and the pending
time decreased as expected.
But the influence of 'sched_interval' is global, setting it too small may
put pressure on slurmctld server. Since we only want quick response on debug
partition (which is designed to let user fre
Mike,
You don't include your entire sbatch script, so it's really hard to say
what's going wrong when we only have a single line to work with. Based
on what you have told us, I'm guessing you are specifying a memory
requirement per node greater than 128000. When you specify a nodelist,
Slurm
Did you every get this resolved? If so, what was the issue? I see this
error:
Can't open PID file /var/run/slurmd.pid (yet?)...ory
I know systemctl shows slurmd running, but I've had some issues with
'systemctl status' and always like to confirm a daemon is running with
'ps'.
Prentice
On 6
... to complete my thought, I don't think what you want to do is
possible. If M is the number of job steps, and N is total jobs, M cannot
be greater than N.
Prentice
On 6/17/21 3:24 PM, Prentice Bisbal wrote:
II know I'm a few weeks late with this response. I actually looked
into this 4-6 w
II know I'm a few weeks late with this response. I actually looked into
this 4-6 weeks ago. According to the Slurm documenntation, an individual
job step counts as a job when evaluating job limits. Pay attention to
the note in the documenation below. From
https://slurm.schedmd.com/slurm.conf.ht
Still no reply to any of my e-mails to the mailing list. I have looked
through the archives, and while traffic there is very light, it's all
questions from people asking for help who never get it. I'm not the only
one who thinks this project is dead:
https://sourceforge.net/p/dmtcp/mailman/dmt
(I apologize if this is a double post, there is conflicting information online
for how to send messages to this list).
Our current cluster is running Centos 7.9 and we are anticipating setting up a
new cluster by the end of the year that will most likely be running one of the
Centos 8.x alterna
Our current cluster is running Centos 7.9 and we are anticipating setting up a
new cluster by the end of the year that will most likely be running one of the
Centos 8.x alternatives (Rocky/Alma/???) with the latest version of Slurm.
Our team is investigating whether it would be appropriate to ru
12 matches
Mail list logo
