User Notes

This cluster is made up of several partitions (queues) that can be accessed via SSH to "seq-login.sabu.mtu.edu." This is the login node/submit node. Partitions/Queues are listed in the Resources tab and vary by cluster. This cluster uses Slurm for job submission/job scheduling.

Keep in mind

• Jobs should always be submitted to a partition/queue and never run directly on the login node.
• Be mindful of storage space.
• Your home direcotry should not exceed 500GB.
• After job completion, or as part of job processing, clean up temporary/scratch files.
• Scratch drives are cleaned and files deleted after 30 days.

Theory of Operation

Slurm is a batch scheduling system designed to schedule the computing resources in a cluster of computers. When users of the Research Computing system submit a prepared job script using the sbatch command from the login node the Slurm scheduler analyzes information about the job from the command line and #SBATCH directives in the job script to determine the resources required for the job. Slurm also tracks the time of submission and the amount of compute time used recently by each user.

When a submitted job is actually executed is determined by:

1. The resources requested: Jobs can only execute when requested resources are available.
2. Time spent in queue: Jobs in the queue longer will have priority.
3. Fair Share: Jobs are balanced to provide a fair share of resources to all users.