[GE users] master node selection and $fill_up behaviour

weiser m.weiser at science-computing.de
Wed Jul 21 13:35:58 BST 2010


Hello Reuti,
Hello Janardhan,

On Wed, Jul 21, 2010 at 01:49:48PM +0530, molumurj wrote:

> What is the load formulae you are using for scheduler? The formulae
> determines the node selection.

Here's my -ssconf:

algorithm                         default
schedule_interval                 0:0:15
maxujobs                          0
queue_sort_method                 seqno
job_load_adjustments              np_load_avg=0.50
load_adjustment_decay_time        0:7:30
load_formula                      np_load_avg
schedd_job_info                   false
flush_submit_sec                  1
flush_finish_sec                  1  
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

> > I'd expect job 144 to be run on node 6. Instead it ends up
> > distributed over nodes 5, 1 and 2:
> how fast are you doing this? The 5 minute average is used by default
> by SGE for the load (middle value of `uptime`).

By hand I was doing all of it within about 30 seconds. I tried a slower,
automated submit routine:

while [ 1 ] ; do echo sleep 100 | qsub --version 6.2u5 -pe dmp 3 ; sleep 30 ; done

Same behaviour. Should I go even slower? Where can I tune to make SGE
cope with semi-fast submits again, as it did in 6.0?

Regards,
-- 
Michael Weiser                science + computing ag
Senior Systems Engineer       Geschaeftsstelle Duesseldorf
                              Martinstrasse 47-55, Haus A
phone: +49 211 302 708 32     D-40223 Duesseldorf
fax:   +49 211 302 708 50     www.science-computing.de
-- 
Vorstand/Board of Management:
Dr. Bernd Finkbeiner, Dr. Roland Niemeier, 
Dr. Arno Steitz, Dr. Ingrid Zech
Vorsitzender des Aufsichtsrats/
Chairman of the Supervisory Board:
Michel Lepert
Sitz/Registered Office: Tuebingen
Registergericht/Registration Court: Stuttgart
Registernummer/Commercial Register No.: HRB 382196

------------------------------------------------------
http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=269473

To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].



More information about the gridengine-users mailing list