[slurm-users] [External] job not running because of "Resources", but resources are available

Prentice Bisbal pbisbal at pppl.gov
Mon Mar 22 01:55:54 UTC 2021


Please post the output of 'scontrol show job 1908239', and also the 
output of 'scontrol show node' for one of the idle compute nodes.

Prentice

On 3/19/21 8:12 PM, Bernstein, Noam CIV USN NRL (6393) Washington DC 
(USA) wrote:
> Can anyone explain why job 1908239 is not running, or what else I can 
> check?  squeue says "Resources", and start time is always right now, 
> no matter when I run "squeue --start", but the resources are available 
> according to "sinfo ... state=idle".  It's only a 1 minute job, so 
> it's not because the nodes won't be available for long enough to be 
> backfilled.
>
> slurm version is admittedly a bit old, 19.05.7
>
>
>     > squeue -p n2019 --state=PD -l
>     Fri Mar 19 20:09:17 2021
>                  JOBID PARTITION     NAME     USER   STATE       TIME
>     TIME_LIMI  NODES NODELIST(REASON)
>                1908239     n2019 LiCu_SPA bernstei  PENDING    
>       0:00      1:00      1 (Resources)
>                1908236     n2019 cspbbr3-  jllyons  PENDING       0:00
>     2-16:00:00      2 (Priority)
>                1908227     n2019 Cy3_dupl   yckim  PENDING       0:00
>     33-08:00:00      4 (Priority)
>                1908231 n2019,n20 sGC_Fe_N bernstei  PENDING       0:00
>     7-00:00:00      4 (JobHeldUser)
>                1908238     n2019 LiCu_SPA bernstei  PENDING    
>       0:00   1:00:00      1 (JobHeldUser)
>
>     > squeue -j 1908239 --start
>                  JOBID PARTITION     NAME     USER ST
>       START_TIME  NODES SCHEDNODES   NODELIST(REASON)
>                1908239     n2019 LiCu_SPA bernstei PD
>     2021-03-19T20:09:17      1 compute-4-[18-19]   (Resources)
>
>     > sinfo -p n2019 state=idle
>     PARTITION AVAIL  TIMELIMIT  NODES  STATE NODELIST
>     n2019        up   infinite     43  alloc
>     compute-4-[0-11,13-17,20-26,28-39,41-47]
>     n2019        up   infinite      5   idle compute-4-[12,18-19,27,40]
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.schedmd.com/pipermail/slurm-users/attachments/20210321/5a2f71f4/attachment.htm>


More information about the slurm-users mailing list