[slurm-users] Getting current memory size of a job

[Mahmood Naderan]

Hi again
May I know why MaxRSS column is empty? Also, which option should I use to
show the name of the second line. What is that?

# sacct -j 827 --format="CPUTime,MaxRSS,Elapsed"
   CPUTime     MaxRSS    Elapsed
---------- ---------- ----------
  20:14:16              01:26:44
  07:13:40              01:26:44
# squeue -j 827
             JOBID PARTITION     NAME     USER ST       TIME  NODES
NODELIST(REASON)
               827    QUARTZ     myQE   ghatee  R    1:27:20      6
compute-0-[0-4],rocks7


Regards,
Mahmood




On Mon, Apr 8, 2019 at 2:26 AM Chris Samuel <chris at csamuel.org> wrote:

> On Sunday, 7 April 2019 10:13:49 AM PDT Mahmood Naderan wrote:
>
> > The output of sstat shows the following error
> >
> > # squeue -j 821
> >              JOBID PARTITION     NAME     USER ST       TIME  NODES
> > NODELIST(REASON) 821   EMERALD g09-test shakerza  R   21:07:18      1
> > compute-0-0 # sstat -j 821 --format="MaxVMSize,AveRSS,AveVMSize,MaxRSS"
> >  MaxVMSize     AveRSS  AveVMSize     MaxRSS
> > ---------- ---------- ---------- ----------
> > sstat: error: no steps running for job 821
>
> This indicates that you are not using "srun" to launch the MPI
> application,
> and also that the MPI stack you are using does not know about Slurm and so
> doesn't know to start itself correctly when you run with mpirun.
>
> All the best,
> Chris
> --
>   Chris Samuel  :  http://www.csamuel.org/  :  Berkeley, CA, USA
>
>
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.schedmd.com/pipermail/slurm-users/attachments/20190410/61a40e3b/attachment.html>