Re: [HTCondor-users] Jobs are reporting cgroups kills at strange limits

["Beyer, Christoph" <christoph.beyer@xxxxxxx>]

Hmm,

you are requesting 1000 MB and using ~ 978 MB it may well be that there was a peak usage above the requested 1000 MB but the slot has provisioned 16000MB - somehow it does not add up without some third party mechanism, also the internal cgroup related memory policy enforcement would remove the job staight away and not put it on hold ...

Best
christoph 

-- 
Christoph Beyer
DESY Hamburg
IT-Department

Notkestr. 85
Building 02b, Room 009
22607 Hamburg

phone:+49-(0)40-8998-2317
mail: christoph.beyer@xxxxxxx

----- UrsprÃngliche Mail -----
Von: svatosm@xxxxxx
An: "HTCondor-Users Mail List" <htcondor-users@xxxxxxxxxxx>, "Christoph Beyer" <christoph.beyer@xxxxxxx>
CC: "vs-admin" <vs-admin@xxxxxx>
Gesendet: Donnerstag, 19. Februar 2026 14:45:44
Betreff: Re: [HTCondor-users] Jobs are reporting cgroups kills at strange limits

Hi,
I have asked about it and we do not have that configured.

Michal

On 19/02/2026 13:20, Beyer, Christoph wrote:
> Hi,
>
> there were some problems in early EL9 versions and condor with correct memory reporting but that is long fixed.
>
> Do you have a sytemperiodic-hold expression configured and if so could you post it ?
>
> Best
> christoph
>