https://grid.fe.up.pt/dokuwiki/ 2026-05-04T07:42:45+00:00 https://grid.fe.up.pt/dokuwiki/ https://grid.fe.up.pt/dokuwiki/lib/tpl/bootstrap3/images/favicon.ico text/html 2024-03-04T15:11:46+00:00 Anonymous (anonymous@undisclosed.example.com) https://grid.fe.up.pt/dokuwiki/doku.php?id=documentation:connecting&rev=1709561506&do=diff Connecting to the cluster This cluster runs a Unix-based operating system, which is text based. The main way to interact with these machines is therefore not through a graphical user interface, as is the case for Windows and MacOS operating systems, but through text-based commands entered in a terminal window. text/html 2016-05-25T15:42:16+00:00 Anonymous (anonymous@undisclosed.example.com) https://grid.fe.up.pt/dokuwiki/doku.php?id=documentation:hints-and-tips&rev=1464183736&do=diff Hints and tips Long running jobs If you have a job that will run for a long time (more than a day) you should first run a test job on a data set and with parameters that are representative of the final problem, but that will complete much quicker. This way you can confirm that your code is syntactically correct and produces results that appear to be correct before you waste weeks or months of CPU time. text/html 2016-05-25T12:51:57+00:00 Anonymous (anonymous@undisclosed.example.com) https://grid.fe.up.pt/dokuwiki/doku.php?id=documentation:resources&rev=1464173517&do=diff Resources The scheduler's job is to make sure the cluster runs as many jobs as possible within the shortest possible time. It does this by planning when to run jobs and on what nodes. It's a bit like the computer game Tetris - the scheduler is trying to pack all of the bricks so that no gaps exist. An important part of this process is telling the scheduler what resources a job requires (or the shape of the Tetris brick) so it can plan its placement. text/html 2020-05-28T11:16:24+00:00 Anonymous (anonymous@undisclosed.example.com) https://grid.fe.up.pt/dokuwiki/doku.php?id=documentation:slurm&rev=1590657384&do=diff Transitioning to SLURM from Maui/Torque THE Grid Feup is changing the cluster to utilize Slurm as its scheduler. There will be some differences to the current setup (Torque/Maui), but it is not a big learning curve. We also provide a wrapper for the Torque commands to run on this Slurm cluster so you can try submitting your current script to the new cluster and notice the difference. text/html 2021-03-03T17:24:06+00:00 Anonymous (anonymous@undisclosed.example.com) https://grid.fe.up.pt/dokuwiki/doku.php?id=documentation:software&rev=1614788646&do=diff Software The cluster runs the Scientific Linux 7 (SL7) distribution, which is based on the commercial Red Hat Enterprise Linux 7 (RHEL7) product. This means that all of the software provided with RHEL7 is available to the cluster as well as any commercial software that supports RHEL7. In addition to this, any free, libre or open source software that targets UNIX environments should also run on the cluster. text/html 2019-11-11T16:47:47+00:00 Anonymous (anonymous@undisclosed.example.com) https://grid.fe.up.pt/dokuwiki/doku.php?id=documentation:submitting-a-job-old-method&rev=1573487267&do=diff Submitting a job (deprecated: see Slurm) Once you have connected to the cluster, you can submit jobs to run on the cluster. A job has two parts: - A script describing what the job does - A description of the resources required to run the job - this describes things like the amount of memory and number of CPUs required by your job text/html 2024-03-14T15:24:15+00:00 Anonymous (anonymous@undisclosed.example.com) https://grid.fe.up.pt/dokuwiki/doku.php?id=documentation:submitting-a-job&rev=1710426255&do=diff Submitting a job Once you have connected to the cluster, you can submit jobs to run on the cluster. A job has two parts: * A script describing what the job does * A description of the resources required to run the job - this describes things like the amount of memory and number of CPUs required by your job