Z.10 Controlling Iterations
Advancing the simulator an iteration, the following happens:
> mschedctl -S
scheduling will stop in 00:00:30 at iteration 1
The scheduler control command, mschedctl, controls various aspects of scheduling behavior. It can be used to manage scheduling activity, kill the scheduler, and create resource trace files. The -S argument indicates that the scheduler run for a single iteration and stop. Specifying a number, n, after -S causes the simulator to advance n steps. You can determine what iteration you are currently on using showstats -v.
> showstats -v
current scheduler time: Mon Feb 16 11:54:03 1998 (887655243)
moab active for 00:01:00 stats initialized on Mon Feb 16 11:53:33
statistics for iteration 1 scheduler started on Wed Dec 31 17:00:00
...
The line that starts with statistics for iteration <X> specifies the iteration you are currently on. Each iteration advances the simulator RMPOLLINTERVAL seconds. By default, RMPOLLINTERVAL is set to 30 seconds.
To see what RMPOLLINTERVAL is set to, use the showconfig command:
> showconfig | grep RMPOLLINTERVAL
RMPOLLINTERVAL 30,30
The showq -r command can be used to display the running (active) jobs to see what happened in the last iteration:
> showq -r
active jobs------------------------
JOBID S PAR EFFIC XFACTOR Q USER GROUP MHOST PROCS REMAINING STARTTIME
fr8n01.804.0 R 1 ------ 1.0 - 529 519 fr9n16 5 00:05:00 Mon Feb 16 11:54:03
fr8n01.187.0 R 1 ------ 1.0 - 570 519 fr7n15 20 1:00:00:00 Mon Feb 16 11:54:03
...
fr8n01.960.0 R 1 ------ 1.0 - 588 519 fr9n11 32 1:00:00:00 Mon Feb 16 11:54:03
9 active jobs 177 of 196 Processors Active (90.31%)
Total jobs: 9
Notice that two new jobs started (without waiting in the eligible queue). Also notice that job fr8n01.187.0, along with the rest that are summarized in the ellipsis, did NOT advance its REMAINING or STARTTIME.
The simulator needs one iteration to do a sanity check. Setting the parameter STOPITERATION to 1 causes Moab to stop after the first scheduling iteration and wait for further instructions.
The showq -i command displays the idle (eligible) jobs.
> showq -i
eligible jobs----------------------
JOBID PRIORITY XFACTOR Q USER GROUP PROCS WCLIMIT CLASS SYSTEMQUEUETIME
fr1n04.362.0* 1 1.0 - 550 519 20 1:00:00:00 batch Mon Feb 16 11:53:33
fr1n04.363.0 1 1.0 - 550 519 20 1:00:00:00 batch Mon Feb 16 11:53:33
fr1n04.365.0 1 1.0 - 550 519 20 1:00:00:00 batch Mon Feb 16 11:53:33
fr1n04.366.0 1 1.0 - 550 519 20 1:00:00:00 batch Mon Feb 16 11:53:33
fr1n04.501.0 1 1.0 - 570 519 20 1:00:00:00 batch Mon Feb 16 11:53:33
fr1n04.580.0 1 1.0 - 570 519 20 1:00:00:00 batch Mon Feb 16 11:53:33
fr1n04.597.0 1 1.0 - 570 519 20 1:00:00:00 batch Mon Feb 16 11:53:33
fr1n04.598.0 1 1.0 - 570 519 20 1:00:00:00 batch Mon Feb 16 11:53:33
fr1n04.602.0 1 1.0 - 570 519 20 1:00:00:00 batch Mon Feb 16 11:53:33
fr1n04.743.0 1 1.0 - 570 519 20 1:00:00:00 batch Mon Feb 16 11:54:03
fr1n04.744.0 1 1.0 - 570 519 20 1:00:00:00 batch Mon Feb 16 11:54:03
fr1n04.746.0 1 1.0 - 570 519 20 1:00:00:00 batch Mon Feb 16 11:54:03
fr1n04.747.0 1 1.0 - 570 519 20 1:00:00:00 batch Mon Feb 16 11:54:03
fr8n01.388.0 1 1.0 - 550 519 20 1:00:00:00 batch Mon Feb 16 11:54:03
14 eligible jobs
Total jobs: 14
Notice how none of the eligible jobs are requesting 19 or fewer jobs (the number of idle processors). Also notice the * after the job id fr1n04.362.0. This means that this job now has a reservation.