Indeed. We use this and BELIEVE that it works, lol!
Bill
function slurm_job_modify ( job_desc, job_rec, part_list, modify_uid )
if modify_uid == 0 then
return 0
end
if job_desc.qos ~= nil then
return 1
end
return 0
end
On
I usually add "withassoc" for a show user
sacctmgr show user loris withassoc
Bill
On 11/23/21 9:07 AM, Loris Bennett wrote:
sacctmgr show user loris accounts
Dammit! Completely forgot that I have these right here in my home
directory! And I probably used your tools last year when I generated
the report.
Thank you Ole for making me remember!
Bill
On 11/10/21 3:08 PM, Ole Holm Nielsen wrote:
On 10-11-2021 16:56, Bill Wichser wrote:
I can't
ow of a way to do cluster reports by partition and I get a
similar error when running the cluster report with partitions options
set. Not sure how it's working for Loris...
- Michael
On Wed, Nov 10, 2021 at 8:34 AM Loris Bennett
mailto:loris.benn...@fu-berlin.de>> wrote:
I can't seem to figure out how to do a query against a partition.
sreport cluster AccountUtilizationByUser user=bill cluster=della, no
issues. Works as expected.
sreport cluster AccountUtilizationByUser Partitions=cpu cluster=della
gives me
Unknown condition: Partitions=cpu
and then print
those jobs with sacctmgr.
https://slurm.schedmd.com/sacctmgr.html
sacctmgr show RunawayJobs
This will list the runaway jobs, and if any will ask if you want to fix
them.
Regards,
Carlos
On Tue, 27 Jul 2021 at 22:49, Bill Wichser <mailto:b...@princeton.edu>> wrote:
[root@della5
[root@della5 bill]# sacctmgr -i delete user mable
Error with request: Job(s) active, cancel job(s) before remove
JobID = 602995 C = tukey A = politics U = mable
Yup, when a user has an active job they cannot be deleted from the
database. The thing is, this cluster tukey has been o
One thing we changed years ago was to think about things differently.
While researchers are in fact buying nodes for the cluster, it's rarely
the case that they get any rights to "their" nodes. Instead they are
buying CPU time in an equivalent way but it gets averaged over 30 days.
We provide
Thanks. Had no problem setting the individual element of the array.
Just thought that it worked differently in the past! Memory apparently
isn't what it used to be!
Thanks again,
Bill
On 6/13/19 10:25 AM, Jacob Jenson wrote:
scontrol show job
# scontrol update jobid=3136818 timelimit+=30-00:00:00
scontrol: error: TimeLimit increment/decrement not supported for job arrays
This is new to 18.08.7 it appears. Am I just missing something here?
Bill
Does anyone on this list run Slurm on the Sierra-like machines from IBM?
I believe they are the ACC922 nodes. We are looking to purchase a
small cluster of these nodes but have concerns about the scheduler.
Just looking for a nod that, yes it works fine, as well as any issues
seen during dep
Yes. We use something like this
if job_desc.features == nil then
job_desc.features = "special"
else
job_desc.features = job_desc.features .. ",special"
end
Bill
On 12/19/2018 09:27 AM, Kevin Manalo wrote:
Is it safe to
The problem is that reservations can be in there yet have no effect on
the submitted job if they would run before the reservation takes place.
One can pull the starting time simply using something like this
scontrol show res -o | awk '{print $2}'
with output
StartTime=2018-06-12T06:00:00
Star
13 matches
Mail list logo
