[torqueusers] HELP: scheduling out of order

scoggins jscoggins at lbl.gov
Wed Oct 17 11:33:34 MDT 2007


I have a user who is submitting several jobs - one at a time.  The  
starttimes are showing up with 99:07:30:06 using
the showstart command.  Some of the other jobs are running but they  
were submitted afterwards.

  diagnose -j 18858

Name                  State Par Proc QOS     WCLimit R  Min      
User    Group  Account  QueuedTime  Network  Opsys   Arch    Mem    
Disk  Procs       Class Features

18858                  Idle ALL   32 nan 99:23:59:59 1   32       
zwu    users        -    18:46:44   [NONE] [NONE] [NONE]    >=0     
 >=0    NC0    [nano:1] [nano]

qstat -u <user>

Job ID               Username Queue    Jobname    SessID NDS   TSK  
Memory Time  S Time
-------------------- -------- -------- ---------- ------ ----- ---  
------ ----- - -----
16650.sched     zwu      nano     tr10al_SZ   25044     8  --     
--    --  R 189:0
18858.sched    zwu      nano     tw20c1_wf     --      8  --    --     
--  Q   --
18872.sched   zwu      nano     tw20_c2       --     12  --    --     
--  Q   --
18982.sched    zwu      nano     d1.2_GWA     2883     4  --    --     
--  R 36:47
19027.sched   zwu      nano     tr10_optic   4915     8  --    --     
--  R 26:41
19059.sched    zwu      nano     tr10al_SZP   6417     8  --    --     
--  R 16:34
19139.sched    zwu      nano     d2.2_abini    --      4  --    --     
--  Q   --


Job scripts looks like

#!/bin/bash

#PBS -l nodes=8:ppn=4:nano
#PBS -N tr10al_SZP
#PBS -M zhigang at berkeley.edu
#PBS -m e

module load siesta
EXE=`which siesta`
NP=`wc -l $PBS_NODEFILE | awk '{print $1}'`
cd $PBS_O_WORKDIR

mpirun -np $NP -hostfile $PBS_NODEFILE  $EXE < rod_szp.fdf > rod_szp.out
cp rod_szp.fdf  rod_szp4.fdf
cp rod_szp.out  rod_szp4.out
cp tr10_Al.DM   rod_szp4.DM
cp tr10_Al.EIG  rod_szp4.EIG
cp tr10_Al.PDOS rod_szp4.PDOS
cp tr10_Al.xyz  rod_szp4.xyz
cp tr10_Al.WFS  rod_szp4.WFS

mpirun -np $NP -hostfile $PBS_NODEFILE  $EXE < rod.fdf > rod.out


Not sure what is happening.

Please help.

Jackie


More information about the torqueusers mailing list