The main problem I see here, is that the submit plugin is called before knowing the execution nodes. If you want to update the wall clock limit depending on the execution nodes you should use the SlurmctldProlog which is executed just before the job starts.
Carles Fenoy On Fri, Dec 2, 2011 at 11:12 AM, Arnau Bria <[email protected]> wrote: > On Wed, 30 Nov 2011 09:53:01 -0700 > Moe Jette wrote: > > Hi Moe, > > > I do not know what your use case is, but perhaps a job submit plugin > > would satisfy your needs: > > http://www.schedmd.com/slurmdocs/job_submit_plugins.html > > That code gets executed directly in the slurmctld daemon. There is > > also a SlurmctldProlog that could be used. Another option would be > > to modify SLURM's code directly, perhaps a minor change to > > select_p_jo_begin in the select plugin: > > http://www.schedmd.com/slurmdocs/selectplugins.html > > thanks for the suggestion. We'll take a look and implement the plugin. > > > Processing 100 requests at the same time should not be a problem. > Great, this will be our workaround. > > Cheers, > Arnau > -- -- Carles Fenoy
