Optimizing jobs¶
The UPPMAX clusters use the Slurm job scheduler. The UPPMAX pages about Slurm here describe how to start a job. However, a job may not have run optimally, i.e. reserving CPU power and/or memory that is not used.
This page describes how to optimize your Slurm jobs.
Commands¶
You will probably have good use of the following commands:
| Command | Description |
|---|---|
| finishedjobinfo | information about finished jobs |
| jobinfo | telling you about running and waiting jobs |
| jobstats | see CPU and memory use of finished job in a plot |
| projinfo | telling you about the CPU hour usage of your projects |
| projmembers | telling you about project memberships |
| projsummary [project id] | summarizes some useful information about projects |
| uquota | telling you about your file system usage |
Working on Snowy? Use -M snowy
For Slurm commands and for commands like projinfo, jobinfo and finishedjobinfo,
you may use the -M flag to ask for the answer to be given
for a system that you are not logged in to.
For example, when logged into Rackham,
you may ask about information about current core hour usage on Snowy,
with the command projinfo -M Snowy