Add seff—the job-efficiency-tracker slurm command—to Trixie?

[abhisheknaik96]

seff is a useful slurm command to check the efficiency of running or past jobs (some documentation)

Sample output:

$ seff 64626
Job ID: 64626
Cluster: stanage.alces.network
User/Group: a_user/clusterusers
State: COMPLETED (exit code 0)
Nodes: 2
Cores per node: 1
CPU Utilized: 00:02:37
CPU Efficiency: 35.68% of 00:07:20 core-walltime
Job Wall-clock time: 00:03:40
Memory Utilized: 137.64 MB (estimated maximum)
Memory Efficiency: 1.71% of 7.84 GB (3.92 GB/core)

Can we have this supported on Trixie? It would be very useful to check the compute- and memory-usage stats for jobs in this manner, especially to ask for the appropriate amount of resources in similar future jobs.

[nrcfieldsa]

Define CR#10290 for internal review.

• seff is a contrib command and is not found in RPM binary packages available to RHEL. (Just OpenSuSE slurm-seff rpm exists, but is not guaranteed to work on EL9)
• It's preferred to install the seff script according to the guidance in GitHub)
• seff has dependency on various additional library unrelated to SLURM libs
• seff may need access to slurm accounting data to perform it's job, this will be confirmed working/tested by NRC KITS RPS prior to hpc user making use of command.

[abhisheknaik96]

Thank you for the update. Looking forward to when the command is tested and set up for use on Trixie.