Hey guys,

Hopefully this is an easy one that maybe others have encountered, we are 
curious if any of the multi-factor priority plugins have trump values over 
others if they are maxed out?

We are running slurm 2.5.4 on a cluster with 640 available slots.

We currently have fairshare set to 5000, counting down to 0, age at 0 counting 
up to 3000, and partition priority same for everyone on  partitions at 8000.

In our example case we are back to our classic problem user that submits 
thousands of jobs to the default partition, and walks away for a week. She 
takes all of the slots immediately available, and the rest of her jobs are 
queued. Her fairshare value drops and as these are lengthy jobs, her age 
increments up...

She hits her maxed value of 11000 (8000 + 3000 + 0) for her jobs waiting in the 
queue.

A new user comes in, submits to the local parition as well... should come in 
with a higher priority by default simply based on the idea that their values 
summed are 8000 for partition, 5000 for fairshare, and 0 for age, so 13000.

And yet we are seeing the jobs at 11000 still jumping the higher priority jobs 
and running... 

We thought perhaps there may be something about maxed out priority values 
jumping the queue, or what exactly we are missing here?

Sample output from sprio -l:

JOBID     USER   PRIORITY        AGE  FAIRSHARE    JOBSIZE  PARTITION        
QOS   NICE

 202545    bem28      11000       3000          0          0       8000         
 0      0
 202546    bem28      11000       3000          0          0       8000         
 0      0
 202547    bem28      11000       3000          0          0       8000         
 0      0
 202548    bem28      11000       3000          0          0       8000         
 0      0
 202549    bem28      11000       3000          0          0       8000         
 0      0
 202550    bem28      11000       3000          0          0       8000         
 0      0
 202551    bem28      11000       3000          0          0       8000         
 0      0
 202552    bem28      11000       3000          0          0       8000         
 0      0
 202553    bem28      11000       3000          0          0       8000         
 0      0
 202554    bem28      11000       3000          0          0       8000         
 0      0
 202555    bem28      11000       3000          0          0       8000         
 0      0
 202556    bem28      11000       3000          0          0       8000         
 0      0
 202653    bem28      11000       3000          0          0       8000         
 0      0
 203965    ter18      12862        402       4460          0       8000         
 0      0
 203967    ter18      12862        402       4460          0       8000         
 0      0
 203969    ter18      12861        402       4460          0       8000         
 0      0
 203971    ter18      12861        402       4460          0       8000         
 0      0
 203973    ter18      12861        402       4460          0       8000         
 0      0
 203975    ter18      12861        402       4460          0       8000         
 0      0
 203977    ter18      12861        402       4460          0       8000         
 0      0
 203979    ter18      12861        402       4460          0       8000         
 0      0
 203981    ter18      12861        402       4460          0       8000         
 0      0


In the example his jobs have been waiting for about 7 hours even... so he has a 
time factor in play too... but as of even a few minutes ago, the first user's 
jobs are still jumping the 2nd users now. So there is something we are missing 
we just don't know what. 

Sample output of squeue:

197043    lowmem full_per    bem28  PD       0:00      1 (Priority)
 197044    lowmem full_per    bem28  PD       0:00      1 (Priority)
 197045    lowmem full_per    bem28  PD       0:00      1 (Priority)
 197046    lowmem full_per    bem28  PD       0:00      1 (Priority)
 197047    lowmem full_per    bem28  PD       0:00      1 (Priority)
 197048    lowmem full_per    bem28  PD       0:00      1 (Priority)
 197049    lowmem full_per    bem28  PD       0:00      1 (Priority)
 197050    lowmem full_per    bem28  PD       0:00      1 (Priority)
 196887    lowmem full_per    bem28   R       3:10      1 hardac-node01-1
 196888    lowmem full_per    bem28   R       3:10      1 hardac-node04-1
 196886    lowmem full_per    bem28   R       3:19      1 hardac-node07-2
 196885    lowmem full_per    bem28   R       7:04      1 hardac-node06-2
 196884    lowmem full_per    bem28   R      11:49      1 hardac-node06-1
 196883    lowmem full_per    bem28   R      13:40      1 hardac-node03-3


Thoughts from any other slurm users would be greatly appreciated.

AC

Reply via email to