Faq t2b: Difference between revisions
No edit summary |
|||
| Line 1: | Line 1: | ||
<br><br> | <br><br> | ||
=== List of the UIs / mX machines: === | === List of the UIs / mX machines: === | ||
- | - m2 , m3 => 20 minutes of CPU time per process <br> | ||
- | - m6 , m7 => 1 hour of CPU time per process | ||
| Line 8: | Line 8: | ||
Add option ' '''-o ServerAliveInterval=100''' ' to your ssh command | Add option ' '''-o ServerAliveInterval=100''' ' to your ssh command | ||
| Line 27: | Line 24: | ||
Note also that if you ask for more than one core your time in the queue will probably be longer as the scheduler needs to find the correct amount of free slots on one single machine. We advise against putting this number higher than one unless you really need it for parallel jobs. | Note also that if you ask for more than one core your time in the queue will probably be longer as the scheduler needs to find the correct amount of free slots on one single machine. We advise against putting this number higher than one unless you really need it for parallel jobs. | ||
=== | === Send a job to the Old PBS local cluster: === | ||
qsub -q localgrid -o script.stdout -e script.stderr [-l walltime=<HH:MM:SS>] myscript.sh | |||
:: | |||
Revision as of 10:10, 8 December 2021
List of the UIs / mX machines:
- m2 , m3 => 20 minutes of CPU time per process
- m6 , m7 => 1 hour of CPU time per process
Keep ssh connection to UI open:
Add option ' -o ServerAliveInterval=100 ' to your ssh command
MadGraph taking all the cores of a workernode
The default settings for MadGraph is to take all the available cores. This kills the site. If the number of cores used by MadGraph is higher than 1, this needs to be asked to the job scheduler with the following directive added to qsub:
-lnodes=1:ppn=2
Where ppn is the number of cores you request.
To tell MadGraph the number of cores he can take per job, use the following recipe:
./bin/mg5_aMC set nb_core 1 #or 2 or whatever you want save options
Note 'nb_core' and 'ppn' must alway be the same value!
Note also that if you ask for more than one core your time in the queue will probably be longer as the scheduler needs to find the correct amount of free slots on one single machine. We advise against putting this number higher than one unless you really need it for parallel jobs.
Send a job to the Old PBS local cluster:
qsub -q localgrid -o script.stdout -e script.stderr [-l walltime=<HH:MM:SS>] myscript.sh