Skip to content
v0.5.1

Agent skills for CBE.next, the Vienna BioCenter HPC cluster: access, Slurm jobs, software, data, job tuning, failure triage, and migration from legacy CBE.

cbe-queue

Explain why a CBE.next Slurm job is pending or waits long to start, and why jobs start in the order they do: job priority, Fair Tree fair-share across holding, institute, lab, and user accounts, usage decay, job age, QOS, backfill, and limits. Use for questions such as why is my job still pending, why is the queue so long, do I get low priority because I submit many jobs, or why did someone else's job start before mine; for pending reasons Priority or Resources, sprio, sshare, and squeue --start estimates. Analyses the user's own pending and recent jobs, including which ones were backfilled. Use cbe-tuning to change resource requests and cbe-triage for failed jobs.

Read SKILL.md at the source

Pinned to revision 5fdb71f11200, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.