This repository includes a collection of functions to assess recent usage statistics on Slurm-based resources and launch Slurm jobs. It contains a mixture of existing open source tools developed elsewhere, and functions developed by CU Boulder Research Computing. Available commands include:
jobstats (job statistics for all jobs run by a specified user over N days)
levelfs (current fair share priority for a specified user)
seff (CPU and RAM efficiency for a specified job; contribued by Slurm and originally developed by Princeton University RC)
seff-array (a wrapper around 'seff-array.py')
seff-array.py (Calculates CPU, memory, and runtime efficiency for job arrays)
suacct (SU usage for each user of a specified account over N days)
suacct_raw (raw SU usage statistics for each user of a specified account over N days using 'sreport')
suuser (SU usage for a specfied user over N days)
We aim to make our online resources accessible to everyone. If you encounter any barriers in the materials contained in this repository, please report them through our support request form https://colorado.service-now.com/req_portal?id=ucb_sc_rc_form