The login nodes should only be used for light computation; any CPU or memory intensive operations should be done using the batch system. A good rule of thumb is that if you wouldn't want to run a task on your personal desktop because it would slow down other applications, you shouldn't run it on the login nodes.
I/O intensive jobs should copy their files to fast, temporary storage, such as the local storage or scratch file system.
When running memory intensive or potentially unstable jobs, we highly recommend requesting whole nodes. By doing so you prevent other users' jobs from being impacted by your job.
- When possible, submitting parallel jobs is preferred. This will lower the time it takes to complete your job freeing up resources for others.
- Respect the privacy of other users; for example, users shall not intentionally seek information on, obtain copies of, or modify files, or passwords belonging to other users unless explicitly authorized to do so by those users.
- Respect the legal protection provided by copyrights and licenses to programs and data; for example, users shall not make copies of a licensed computer program to avoid paying additional license fees.
- Respect the intended usage for which access to computing resources was granted; for example, users shall use accounts authorized for their use by the principal investigator responsible for these accounts only for the purposes specified by the principal investigator and shall not use any other user's account unless explicitly authorized to do so by the Faculty/PI.
- Respect the integrity of computing systems; for example, users shall not intentionally develop or use programs that harass other users or infiltrate a computer or computing systems or damage or alter the software components of a computing system.
- Respect the financial structure of computing systems; for example, users shall not intentionally develop or use any unauthorized mechanisms to alter or avoid charges levied by DoIT for computing services.
- Do not provide commercial companies with access to the Central HPC by simply allowing the commercial company to use their accounts.
In general, we just encourage our users to remember that what you do may affect other researchers on the system. If you think something you want to do or try might interfere with the work of others, we highly recommend that you contact us at ITS-HPCSupprt@csulb.edu.