Jobs not Submitting or Visible on Lawrence

Summary

What to do when sbatch won't accept your job and squeue won't display queued jobs.

Body

Issue/Question

Lawrence cannot see queue or submit jobs

slurm_load_jobs error: Unable to contact slurm controller (connect failure)

Environment

  • Lawrence
  • HPC

Cause

slurm controller (connect failure)

Resolution

  1. Contact the Service Desk and inform them of the outage

ITS STAFF ONLY

  1. Follow  Restarting slurmctld on Lawrence
 

Details

Details

Article ID: 3668
Created
Thu 8/8/19 8:27 AM
Modified
Thu 2/18/21 12:46 PM
KCS Article Status
WIP: Only Problem & some Environment captured
Not Validated: Complete & Resolution captured, confidence lacks in structure, content, no feedback
Validated: Complete & reusable, used by licensed KCS user, confidence in resolution & std. compliance
Validated