If you read nothing else, read this. This page is an insanely simple guide to just barely get you going. The documentation on this page will not be complete. It will not tell you everything. It will tell you just enough to get started with using Research Computing Cluster, SPORC (Scheduled Processing on Research Computing). First off, email email@example.com if you encounter any issues with the cluster.
Research Computing also has a wiki site! It has much of the same information as the official site, but not the questionnaire, My Projects tab, or RIT branding aesthetic. You can consider the wiki site the definitive source of our documentation. It also has some of our more technical information, like what SPORC is made of and its testing results.
If you are unfamiliar with the topic of research computing or want to know more about what we offer check out our Services and About page.
Slurm Account vs Users
First we will clarify some important terminology to help you understand the steps to getting started.
A slurm Account is a tool for controlling the resources allocated to a user or a group of users. For example, if a researcher was requesting resources, an Account would have to be made, and that researcher's User would have to be added to that Account. Furthemore, if the researcher wanted some students to be able to use the same resources, they would also have to become a User, and have their Users be added to the same Account.
A User is simply a way to connect your RIT credentials and account to the slurm environment. *Important* having a User and being able to log in to sporcsubmit does not mean you have been allocated resources, until you have been added to an Account.
First Time Users
If this is your first time using Research Computing Resources, you will first have to login to Sporc to create a user home directory. You can do this by following this documentation using your standard RIT credentials. *NOTE* this user will not be able to do anything on RC resources until it has been added to a Slurm account.
Research Computing aims to know the researchers, their research, and their computational and research computing needs. To be granted an account make sure to fill out this questionnaire so we can provide what you need for your project.
Logging in to Research Computing
Now that you have an account, you are ready to get onto our cluster, SPORC. To log into SPORC or other Research Computing provided resources, you will need to use either SSH or FastX. The first time you access SPORC, I would recommend you do it through SSH. FastX is useful for when you need a graphical interface, such as when you are visualizing data or analyzing graphs. When you log into SPORC there will be a message of the day that contains helpful tips and important information, so make sure you read it. You can view the message anytime by running motd. Remember: the host name for SPORC is sporcsubmit.rc.rit.edu.
Whether you logged in with SSH or FastX, it important that you know how to navigate the terminal. Through the terminal you will do most of the work for your research with Research Computing, including creating and editing files, loading software, and running jobs. If you have never used a terminal before, start by learning some Basic Unix Commands and how to use a Text Editor.
Linux and Mac users have a built-in command for transferring files over SSH, but there are applications available for every platform to do the same thing. We currently provide documentation for using FileZilla and in the future we will be using Globus. However, these are not your only option; if you are logged onto a computer with a graphical interface via FastX you can use web applications like Dropbox.
Slurm is the software we use to manage your research computation on SPORC. You tell it what resources you need (read this if you need help determining what you need), and it dispatches your work to one or more computers that make up SPORC, and then the program runs to completion. When your work is done, Slurm frees up those resources so that someone else can use them. Below we have outlined two ways to submit jobs. Before writing and submitting your first job, become familiar with how to view your jobs and the resources available on SPORC.
This is the preferred method for creating work for the Research Computing Cluster. An SBATCH file consists of some commands telling Slurm what resources you need, followed by the Linux commands necessary to perform the requested work. Here you can tell Slurm how many cores (CPU) you need and how much memory (RAM), as well as how long to let your job run before it has taken too long. This file can then be run using the "sbatch" command to submit it to the Slurm Queue.
For example SBATCH files, please run "grab-examples" from the command line. This will create the folder "slurm-examples" in your Home Directory which contain scripts the demonsrate the basic usage of the cluster. NOTE: Since the examples were made, we have changed the name of our partitions (groups of certain computers). Instead of #SBATCH -p work -n 4 use #SBATCH -p <tier1/tier2/tier3/onboard/debug> -n 4.
Using Interactive Mode (sinteractive)
If you need user interaction or are only running something once then run `sinteractive`. This will ask you for the resources you require and then connect you to the scheduled node. If you don't know what that entails, just try it. Be sure to exit from your sinteractive session by running exit when you're done, otherwise you're a terrible person for requesting resources you aren't using. For the full process, see our documentation.
Try to avoid requesting more resources than you need on the cluster. Any resources that you tell Slurm you're going to use cannot be offered to other users regardless of whether you actually use those resources. If you fudge your numbers too much, you're eligible to have your allocation terminated by admins.
"sinteractive" is not the best way to run jobs by any means. For any sort of repeatable workflow, you will need to write SBATCH jobs.
Your research more than likely needs software, whether it's for creating, analyzing, or visualizing data. So before you start researching, you need to learn how to use modules. Modules are the way Research Computing provides a lot of software without it all conflicting with each other. If you need it, we might have it. If we don't have it email us at firstname.lastname@example.org.
If you need help using any Research Computing resources, don't hesitate to stop by our lab. Our infrastructure is changing all the time and our documentation may not always be up-to-date. We're more than happy to work with you to accommodate your research needs.