Re: [gridengine users] m_mem_free and cgroups

2020-08-07 Thread Ondrej Valousek
, but kernel oom killer can reap the task if is too memory hungry. HTH, Ondrej Get Outlook for Android<https://aka.ms/ghei36> From: berg...@merctech.com Sent: Friday, August 7, 2020 7:11:11 PM To: Ondrej Valousek Cc: users@gridengine.org ; Trimboli, Davi

Re: [gridengine users] m_mem_free and cgroups

2020-08-07 Thread Ondrej Valousek
Short answer: Use a different tool than stress Long answer: linux kernel is too clever for tests like stress because allocating a memory is one thing (which is taken only like "alright, i'll see what i can do, here is the pointer") but actually _using_ that memory is something completely differe

Re: [gridengine users] CPU and Mem usage for interactive jobs

2019-12-09 Thread Ondrej Valousek
I think using addgrp is nowadays an obsolete and too complicated strategy (at least for exec machines running RHEL-7 or newer). I have patched SoGE to start jobs using systemd and also use systemd to collect job stats. It is no longer using PDC to collect job stats. AFAIK something similar should

Re: [gridengine users] limit CPU/slot resource to the number of reserved slots

2019-08-29 Thread Ondrej Valousek
tting. On big SMP boxes it may > >> actually cause more instability. Anyway, jobs should be configured to use > >> exact amount of threads they request, and it should be monitored. > >> > >> Best regards, > >> Mikhail Serkov > >>

Re: [gridengine users] limit CPU/slot resource to the number of reserved slots

2019-08-29 Thread Ondrej Valousek
affinity setting. On big SMP boxes it may actually >> cause more instability. Anyway, jobs should be configured to use exact >> amount of threads they request, and it should be monitored. >> >> Best regards, >> Mikhail Serkov >> >>> On Aug 29, 2019

Re: [gridengine users] limit CPU/slot resource to the number of reserved slots

2019-08-29 Thread Ondrej Valousek
:28 AM To: Ondrej Valousek Cc: Dietmar Rieder ; users@gridengine.org Subject: Re: [gridengine users] limit CPU/slot resource to the number of reserved slots Also, something to keep in mind - cgroups will not solve this issue completely. It is just affinity enforcement. If the job spawns multiple

Re: [gridengine users] limit CPU/slot resource to the number of reserved slots

2019-08-29 Thread Ondrej Valousek
; Ondrej Valousek ; users Subject: Re: [gridengine users] limit CPU/slot resource to the number of reserved slots Great, thanks so much! Dietmar Am 29. August 2019 09:05:35 MESZ schrieb Ondrej Valousek mailto:ondrej.valou...@adestotech.com>>: Nope, SoGE (as of 8.1.9) supports CGROUPS w

Re: [gridengine users] limit CPU/slot resource to the number of reserved slots

2019-08-29 Thread Ondrej Valousek
: Daniel Povey Sent: Monday, August 26, 2019 10:12 PM To: Dietmar Rieder ; Ondrej Valousek ; users Subject: Re: [gridengine users] limit CPU/slot resource to the number of reserved slots I don't think it's supported in Son of GridEngine. Ondrej Valousek (cc'd) described in the first t

[gridengine users] SGE systemd integration - can I contribute my patches?

2019-08-23 Thread Ondrej Valousek
more testing. Now can I send my patches somewhere so it can be possibly merged with the SoGE main repo? Thanks, Ondrej From: Ondrej Valousek Sent: Friday, August 9, 2019 1:40 PM To: 'users@gridengine.org' Subject: SGE & systemd integration Hi all, I am thinking of making SGE (o

[gridengine users] SGE & systemd integration

2019-08-09 Thread Ondrej Valousek
Hi all, I am thinking of making SGE (or sge_execd) more systemd friendly. Right now, there is some (as per 8.1.9) support for cgroups as per: USE_CGROUPS=y/n My proposal is to make it: USE_CGROUPS=y/n/systemd when set to systemd, we would not to detect and any cgroups (and setting cpuset controll