Repository navigation
Open
Description
Hello torque users and developers
I upgrade torque to new version(6.1.1) and I got some problems
Suppose that I submit job with command
qsub -l nodes=1:ppn=25 my_script.sh
than pbstop shows status with filled slots as much as jobs*#ofppns
but it shows like this
Usage Totals: 5/264 Procs, 5/5 Nodes, 8/40 Jobs Running
Node States: 5 free
CPU 0
1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0
---------------------------------------------------------------
shepherd2 . . . . . . . . . . . . . . . . . . . . . . . . R . . . . .
shepherd2 . . . . . . . . . . . . . . . . . .
---------------------------------------------------------------
1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0
---------------------------------------------------------------
shepherd3 . . . . . . . . . . . . . . . . . . . . . . . . C . . . . .
shepherd3 . . . . . . . . . . . . . . . . . .
---------------------------------------------------------------
It shows only one Proc per job is used in torque system, tho I write command as ppn=25.
Here's qstat result
Job ID Username Queue Jobname SessID NDS TSK Memory Time S Time
----------------------- ----------- -------- ---------------- ------ ----- ------ --------- --------- - ---------
673.shepherd dlsrnsi batch snakejob.run_mod 79340 1 25 -- -- R 00:00:00
695.shepherd dlsrnsi batch snakejob.run_mod 45783 1 25 -- -- R 00:00:00
696.shepherd dlsrnsi batch snakejob.run_mod 45866 1 25 -- -- R 00:00:00
697.shepherd dlsrnsi batch snakejob.run_mod 82416 1 25 -- -- R 00:00:00
698.shepherd dlsrnsi batch snakejob.run_mod 42329 1 25 -- -- R 00:00:00
699.shepherd dlsrnsi batch snakejob.run_mod 171979 1 25 -- -- R 00:00:00
700.shepherd dlsrnsi batch snakejob.run_mod 172166 1 25 -- -- R 00:00:00
701.shepherd dlsrnsi batch snakejob.run_mod 3387 1 25 -- -- R 00:00:00
702.shepherd dlsrnsi batch snakejob.run_mod -- 1 25 -- -- Q --
703.shepherd dlsrnsi batch snakejob.run_mod -- 1 25 -- -- Q --
It has some problem in checking elap time.
and here is my queue option. (Acutally I don't have much idea with queue). I think it would be source of problem
create queue batch
set queue batch queue_type = Execution
set queue batch max_running = 1000
set queue batch resources_max.nodect = 1000
set queue batch resources_max.ncpus = 48
set queue batch resources_max.nodes = 2
set queue batch resources_max.neednodes = 1:ppn=48
set queue batch resources_max.procct = 1000
set queue batch resources_min.ncpus = 1
set queue batch resources_min.procct = 1
set queue batch resources_default.ncpus = 1
set queue batch resources_default.neednodes = batch
set queue batch resources_default.nodect = 1
set queue batch resources_default.nodes = 1
set queue batch resources_default.procct = 1000
set queue batch resources_available.nodect = 1000
set queue batch resources_available.procct = 1000
set queue batch resources_available.nodes = 1:ppn=50
set queue batch enabled = True
set queue batch started = True
Thank you for reading
Ingoo Lee
Metadata
Metadata
Assignees
Labels
No labels
Activity