Hola Alfonso,

Do you have backfilling enabled? Do all the jobs have a timelimit set?
Backfilling can only work if the jobs have a timelimit set, either by
specifying it of using the partition max time limit. If you do not have
backfilling enabled, jobs will follow the priority order. So I will
recomend checking the backfilling and the job timelimit and see if that is
the reason for the smaller jobs to not start.

Saludos,
Carles Fenoy
Barcelona Supercomputing Center


On Mon, Apr 29, 2013 at 10:25 AM, Alfonso Pardo <[email protected]>wrote:

>   Hello!
>
> I have a cluster with 15 nodes and slurm multifactor policy:
>
> *# JOB PRIORITY*
> *PriorityType=priority/multifactor*
> *PriorityFavorSmall=YES*
> *PriorityUsageResetPeriod=NONE*
> *PriorityWeightAge=1000*
> *PriorityWeightFairshare=1000*
> *PriorityWeightJobSize=10000*
> *PriorityWeightPartition=1000*
> *PriorityDecayHalfLife=0*
> *PriorityMaxAge=7-0*
> *PriorityWeightQOS=1*
> *EnforcePartLimits=YES*
> *PreemptMode=Checkpoint*
> *PreemptType=preempt/qos*
>
> If I have 2 jobs running (left 13 nodes no allocated) and I submit a job
> than request 14 nodes it will wait for free resources. But during this
> waiting I submit another job than only request 1 node, the new job will
> wait becouse has less priority than the 14-requested-job, althought I have
> nodes in IDLE state.
>
> For example (squeue):
>
> 248790  test job3  user3  PD       0:00      1 (Priority)
> 249991  test job3  user3  PD       0:00      1 (Priority)
> 250096  test job3  user3  PD       0:00      1 (Priority)
> 242962  test job2  user2  PD       0:00     14 (Resources)
> 242879  test job1  user1   R 2-23:34:46      1 bc-p3-01
> 242930  test job1  user1   R 2-23:34:46      1 bc-p4-01
>
> And my sinfo:
>
> PARTITION    AVAIL  TIMELIMIT  NODES  STATE NODELIST
> test*       up   infinite      2  alloc bc-p3-01,bc-p4-01
> test*       up   infinite     12   idle
> bc-p10-01,bc-p11-01,bc-p12-01,bc-p13-01,bc-p14-01,bc-p15-01,bc-p16-01,bc-p17-01,bc-p18-01,bc-p5-01,bc-p6-01,bc-p9-01
>
> Have I a erroneous configuration?
>
>
> Thanks in advance!!!!
>
>
>
>
>
> *Alfonso Pardo D�az*
> *Researcher / System Administrator at CETA-Ciemat *
> *c/ Sola n� 1; 10200 Trujillo, ESPA�A*
> *Tel: +34 927 65 93 17 Fax: +34 927 32 32 37*
>
> [image: CETA-Ciemat logo] <http://www.ceta-ciemat.es/>
> ---------------------------- Confidencialidad: Este mensaje y sus ficheros
> adjuntos se dirige exclusivamente a su destinatario y puede contener
> informaci�n privilegiada o confidencial. Si no es vd. el destinatario
> indicado, queda notificado de que la utilizaci�n, divulgaci�n y/o copia
> sin autorizaci�n est� prohibida en virtud de la legislaci�n vigente.
> Si ha recibido este mensaje por error, le rogamos que nos lo comunique
> inmediatamente respondiendo al mensaje y proceda a su destrucci�n.
> Disclaimer: This message and its attached files is intended exclusively for
> its recipients and may contain confidential information. If you received
> this e-mail in error you are hereby notified that any dissemination, copy
> or disclosure of this communication is strictly prohibited and may be
> unlawful. In this case, please notify us by a reply and delete this email
> and its contents immediately. ----------------------------
>



-- 
--
Carles Fenoy

Reply via email to