Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
public:lofar_processing_juelich [2015-08-10 13:08]
Stefan Froehlich [LOFAR Software]
public:lofar_processing_juelich [2017-03-08 15:27] (current)
Line 32: Line 32:
  
 ==== SRM Copy ==== ==== SRM Copy ====
-For data acquisition with grid-tools please use the Judac system. Your account for Jureca will also work for Judac.+For data acquisition with grid-tools please use the Judac system. Your account for Jureca will also work for Judac.\\
 [[http://​www.fz-juelich.de/​ias/​jsc/​EN/​Expertise/​Datamanagement/​JUDAC/​JUDAC_node.html]] [[http://​www.fz-juelich.de/​ias/​jsc/​EN/​Expertise/​Datamanagement/​JUDAC/​JUDAC_node.html]]
  
Line 38: Line 38:
 To use the grid-proxies simple follow these steps:\\ To use the grid-proxies simple follow these steps:\\
 Store your private key in ''​$HOME/​.globus/​userkey.pem''​\\ Store your private key in ''​$HOME/​.globus/​userkey.pem''​\\
-Execute:\\ <​code>​chmod ​600 $HOME/​.globus/​userkey.pem</​code>​+Store your signed certificate in ''​$HOME/​.globus/​usercert.pem''​\\ 
 +Execute:\\ 
 +<​code>​ 
 +chmod 400 $HOME/​.globus/​userkey.pem 
 +chmod 600 $HOME/​.globus/​usercert.pem 
 +</​code>​
 Store your signed certificate in ''​$HOME/​.globus/​usercert.pem''​\\ Store your signed certificate in ''​$HOME/​.globus/​usercert.pem''​\\
 Then you have to generate a proxy. Then you have to generate a proxy.
Line 68: Line 73:
 "​gsm"​ and pass "​msss"​\\ "​gsm"​ and pass "​msss"​\\
 \\ \\
 +To run your jobs on the compute nodes you first have to setup and submit
 +a job via the batch system. A detailed description can be found on the
 +Jureca homepage \\
 +[[http://​www.fz-juelich.de/​ias/​jsc/​EN/​Expertise/​Supercomputers/​JURECA/​UserInfo/​QuickIntroduction.html?​nn=1803700]]
 +
 +When configuring the resources on the system please use only the '​--nnodes'​ option. Ignore '​--ntasks',​ '​--ntasks-per-node'​ and '​--cpus-per-task'​. A (for the moment) working configuration is implemented in the framework itself.\\
 +To run a generic pipeline on multiple nodes configure the pipeline as follows:
 +In your '​pipeline.cfg'​ configure
 +<​code>​
 +[remote]
 +method = slurm_srun
 +max_per_node = 1
 +</​code>​
 +Set '​max_per_node'​ individually for every step in your parset to the number tasks you want to (can) run per node.
  • Last modified: 2015-08-10 13:08
  • by Stefan Froehlich