This howto briefly describes how you can do remote IO leveraging the Condor-integrated condor_chirp and {link: http://www.cse.nd.edu/~ccl/software/parrot/ Parrot}. All of this should work with Condor versions 7.6.0 and newer. {subsection: What is required?} -In order to do this, all you need is Condor in version 7.6.0 or newer and you need {link: http://www.cse.nd.edu/~ccl/software/parrot/ Parrot}. You will need to have the version matched to your execute node architectures available. It is more convenient to install parrot directly on the execute nodes but you can also transfer it with your job data. A small caveat: Parrot will only work on Linux, which means that your execute machine needs to run some flavor of Linux. Your submit node, however, can run whatever OS that is supported by Condor 7.6.0. +In order to do this, all you need is Condor version 7.6.0 or newer and you need {link: http://www.cse.nd.edu/~ccl/software/parrot/ Parrot}. You will need to have the version matched to your execute node architectures available. It is more convenient to install parrot directly on the execute nodes but you can also transfer it with your job data. A small caveat: Parrot will only work on Linux, which means that your execute machine needs to run some flavor of Linux. Your submit node, however, can run whatever OS that is supported by Condor 7.6.0. {subsection: How to create your submit file?} To have your job do remote IO, all you now need to do is to create a wrapper such that your job can be run under parrot. The easiest way is to have a script such as @@ -20,7 +20,7 @@ # its arguments into 'parrot_run' #################################### -./parrot_run $@ +./parrot_run "$@" {endcode}