Re: [slurm-dev] Small jobs waitingThanks Carles, It’s work! I have change the 
Schedule to Backfill and my small jobs is running allocating the IDLE nodes.

Thanks again!!!

From: Carles Fenoy 
Sent: Monday, April 29, 2013 10:40 AM
To: slurm-dev 
Subject: [slurm-dev] Re: Small jobs waiting

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 


  ---------------------------- 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