So, if I reinstall using the Berkeley DB spooler, will this mitigate this kind
of problem, or will the qmaster still want to commit hara-kiri by trying to
load everything into memory from the DB?
Mfg,
Juan Jimenez
System Administrator, BIH HPC Cluster
MDC Berlin / IT-Dept.
Tel.: +49 30 9406 2800
On 27.06.17, 10:41, "William Hay" <w....@ucl.ac.uk> wrote:
On Tue, Jun 27, 2017 at 08:30:55AM +0000, juanesteban.jime...@mdc-berlin.de
wrote:
> Never mind. One of my users submitted a job with 139k subjobs.
>
> A few other questions:
>
> 1) Is it possible to stop a job submission if I know it???s going to make
the qmaster croak?
Not sure exactly what you mean but setting max_u_jobs and max_aj_tasks in
the grid engine configuration
should allow you to control job submission to a degree. Also user
education could be helpful
array jobs should put less stress on the qmaster than lots of individual
jobs.
> 2) Will switching to the berkeley DB setup in the qmaster alleviate this?
> 3) Can that be done and still retain the existing data in /opt/sge?
I believe spool type can only be chosen when initially setting up SGE so no.
William
_______________________________________________
SGE-discuss mailing list
SGE-discuss@liv.ac.uk
https://arc.liv.ac.uk/mailman/listinfo/sge-discuss
