[gridengine users] GE 2011.11p1 -- issue with scheduler configuration

Karun K hpcmonk at gmail.com
Sun Dec 1 19:03:06 UTC 2013


Yes, all execution hosts have complex value slots




On Thu, Nov 28, 2013 at 10:51 AM, Reuti <reuti at staff.uni-marburg.de> wrote:

> Hi,
>
> Am 26.11.2013 um 22:14 schrieb Karun K:
>
> > We are trying to change the scheduler config to "least_used_host" policy
> instead of load policy. Changed the following in scheduler config, as per
> > http://wiki.gridengine.info/wiki/index.php/StephansBlog
>
> The syntax is a little bit broken there. You attached the "slots" complex
> also to each execution host's definition?
>
> -- Reuti
>
>
> > But the jobs are still being submitted using "fill_up_host" policy. We
> are using smp pe environment, including smp pe configuration too.
>
> > Am I missing anything else ? Any suggestions would be a great help.
> >
> > Thanks!
> >
> >
> > root at login-0-0 ~]# qconf -ssconf
> > algorithm                         default
> > schedule_interval                 0:0:15
> > maxujobs                          0
> > queue_sort_method                 load
> > job_load_adjustments              NONE
> > load_adjustment_decay_time        0:0:0
> > load_formula                      -slots
> > schedd_job_info                   true
> > flush_submit_sec                  0
> > flush_finish_sec                  0
> > params                            none
> > reprioritize_interval             0:0:0
> > halftime                          168
> > usage_weight_list                 cpu=1.000000,mem=0.000000,io=0.000000
> > compensation_factor               5.000000
> > weight_user                       0.250000
> > weight_project                    0.250000
> > weight_department                 0.250000
> > weight_job                        0.250000
> > weight_tickets_functional         0
> > weight_tickets_share              0
> > share_override_tickets            TRUE
> > share_functional_shares           TRUE
> > max_functional_jobs_to_schedule   200
> > report_pjob_tickets               TRUE
> > max_pending_tasks_per_job         50
> > halflife_decay_list               none
> > policy_hierarchy                  OFS
> > weight_ticket                     0.010000
> > weight_waiting_time               0.000000
> > weight_deadline                   3600000.000000
> > weight_urgency                    0.100000
> > weight_priority                   1.000000
> > max_reservation                   0
> > default_duration                  INFINITY
> >
> >
> > [root at login-0-0 ~]# qconf -sp smp
> > pe_name            smp
> > slots              9999
> > user_lists         NONE
> > xuser_lists        NONE
> > start_proc_args    /bin/true
> > stop_proc_args     /bin/true
> > allocation_rule    $pe_slots
> > control_slaves     FALSE
> > job_is_first_task  TRUE
> > urgency_slots      min
> > _______________________________________________
> > users mailing list
> > users at gridengine.org
> > https://gridengine.org/mailman/listinfo/users
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://gridengine.org/pipermail/users/attachments/20131201/11ce6b5c/attachment.html>


More information about the users mailing list