e end up with high IO wait
so identifying the culprit requires also comparing total IO per job.
William Dear
From: slurm-users on behalf of Loris
Bennett
Sent: Tuesday, May 17, 2022 12:46 AM
To: Slurm User Community List
Subject: Re: [slurm-users] Performanc
ince it only runs 100 at a
time but all the pending array jobs still show up as waiting. If the partition
resources are too low and the job is running less than 100 then it actually is
waiting on another job. The challenge will be determining when a job is self
limiting vs waiting on
the job is complete I would like to see run time and peak RAM
usage per task so that we can correctly size the reservations for future jobs.
It would also be very helpful to break this down by node so that I can identify
poorly performing nodes.
William Dear
I have several phantom jobs in "sreport user" that always show up even during
periods when no jobs were running. I don’t know the job IDs and would
appreciate suggestions for identifying the jobs and fixing the database. My
cluster accounting is uses slurmdbd with mariadb.
sreport user TopU
