Stefano Bridi <[email protected]> writes: > Hi all, is there a way to use the scratch area (local disk) on the > compute node in a transparent way from the submitted script point of > view? > What I want to do is to copy to and from the compute node scratch area > the job data using the prolog/epilog but I need also to start the > submitted script in the scratch area instead of the cwd. > Is there a way?
Why can't you just cd into TMPDIR, or whatever the scratch area is, in the script? Otherwise, if you have a scratch directory known at submission time, isn't the -wd argument good enough? To change the working directory at run time, you'd have to mess with its definition in the job spool area in the prolog; the prolog will run in the original one, I think. -- Community Grid Engine: http://arc.liv.ac.uk/SGE/ _______________________________________________ users mailing list [email protected] https://gridengine.org/mailman/listinfo/users
