Re: [slurm-users] introduce short delay starting multiple parallel jobs with srun

2017-11-10 Thread Loris Bennett
t 03:46:23PM +0100, Yakupov, Renat /DZNE wrote: >> I tried that. It doesnt even queue the job with an error: >> sbatch: unrecognized option '--array=1-24' >> sbatch: error: Try help for more information. > > what version of slurm are you using? > Regards > -- > Gennaro

Re: [slurm-users] [slurm-dev] sacct: --unit applied to NNodes

2017-11-27 Thread Loris Bennett
Loris Bennett <loris.benn...@fu-berlin.de> writes: > Hi, > > With version 16.05.10-2, the option '--units' get applied incorrectly to > the column 'NNodes': > > $ sacct -u user1234 -o jobid,nnodes,ncpus,reqmem,maxrss,elapsed -S 2017-07-01 > --units=G >JobID

Re: [slurm-users] Slurm fair share priority not being applied

2017-11-30 Thread Loris Bennett
_multifactor.html doesn't seem to mention setting things up with 'sacct'. Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] lmod and slurm

2017-12-19 Thread Loris Bennett
reas the module 'rusty_and_old' would contain module add tensorflow/0.1 module add cuda/0.2 Would that help? Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] lmod and slurm

2017-12-19 Thread Loris Bennett
to run the "module add ${SLURM_CONSTRAINT}" or > remove the unwanted modules that were loaded (maybe automatically) on > the submission node and aren't working on the execution node. > > Thanks, > Yair. > > On Tue, Dec 19 2017, "Loris Bennett" <loris.be

Re: [slurm-users] lmod and slurm

2017-12-19 Thread Loris Bennett
myprogram >>> >>> So they get the tensorflow version (and PATH/PYTHONPATH) of the >>> submission node's version of tensorflow (and any additional default >>> modules). >>> >>> There is never a chance to run the "module add ${SLURM_CO

Re: [slurm-users] QOS Filter

2017-11-17 Thread Loris Bennett
so the QOS could not be automatically selected based on the run-time. So what would be the use case for the automatic selection? Regards Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Limit size submission script

2017-11-09 Thread Loris Bennett
> performance. > > > > On 11/09/2017 03:56 AM, sysadmin.caos wrote: >> Hello, >> >> A researcher that is using a SLURM cluster (version 17.02.7) has created a >> submit script whose size is 8 MB (yeah!!). I have read SLURM has a limit >> size in 4

Re: [slurm-users] [slurm-dev] sacct: --unit applied to NNodes

2017-12-07 Thread Loris Bennett
Hi Chris, Chris Samuel <ch...@csamuel.org> writes: > On Thursday, 7 December 2017 8:09:12 PM AEDT Loris Bennett wrote: > >> Has this issue been addressed in any subsequent versions? > > No change in 17.11.0. > > $ sacct -u csamuel -o jobid,nnodes,ncpus,reqme

Re: [slurm-users] [slurm-dev] sacct: --unit applied to NNodes

2017-12-07 Thread Loris Bennett
Loris Bennett <loris.benn...@fu-berlin.de> writes: > Loris Bennett <loris.benn...@fu-berlin.de> writes: > >> Hi, >> >> With version 16.05.10-2, the option '--units' get applied incorrectly to >> the column 'NNodes': >> >> $ sacct -u user1234 -

[slurm-users] sacctmgr - bug listing accounts?

2018-04-27 Thread Loris Bennett
, in the second case, 'geochemie' is missing. I'm using version 17.02.10. Is this a bug? Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

[slurm-users] sshare: Fairshare=parent leads to multiple entries with NormShares=1

2018-05-23 Thread Loris Bennett
that the individual users have the same NormShares as their parent and grandparent, but on the other it contradicts my understanding of NormShares, which is the fraction of the total shares that an account or user has. Can anyone shed any light on this? Cheers, Loris -- Dr. Loris Bennett (Mr

[slurm-users] Update via 'sacctmgr load'?

2018-05-23 Thread Loris Bennett
this file with 'sacctmgr'? Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] sacctmgr - bug listing accounts?

2018-06-07 Thread Loris Bennett
Loris Bennett writes: [snip (93 lines)] > Unfortunately sacctmgr just doesn't list 'geochemie' as being an > account. It only appears as the parent of the research groups which are > below it in the hierarchy: > > $ /usr/bin/sacctmgr -or show accounts | egrep 'geo|Acc|---'

Re: [slurm-users] allocate more resources for a current interactive job

2018-06-18 Thread Loris Bennett
e where the job is located has 120 Gb and 4 cores available. > > I just want to use more cores and more RAM for such shell session without > having > to terminate it. As far as I know, this is not currently possible. Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Uni

Re: [slurm-users] Memory prioritization?

2018-06-12 Thread Loris Bennett
ing wasted. HTH, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Using free memory available when allocating a node to a job

2018-05-29 Thread Loris Bennett
e to them individually. Pointing out that memory overestimation not only hampers other users' job but also their own usually helps. Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Running 'scontrol reconfigure" while jobs are running

2018-05-28 Thread Loris Bennett
/etc/slurm/slurm.conf. > > Can anybody confirm that there is no impact? Reconfigure does not impact jobs. Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Update via 'sacctmgr load'?

2018-05-27 Thread Loris Bennett
in > > Sent from Samsung tablet. > > ---- Original message > From: Loris Bennett <loris.benn...@fu-berlin.de> > Date: 23/05/2018 13:54 (GMT+01:00) > To: Slurm Users Mailing List <slurm-us...@schedmd.com> > Subject: [slurm-users] Update via 'sacctmgr

Re: [slurm-users] Permissions to administer slurm

2018-05-03 Thread Loris Bennett
ur specific errors, but you can define the roles 'user', 'operator', and 'admin' as described here: https://slurm.schedmd.com/user_permissions.html Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] sacctmgr - bug listing accounts?

2018-04-30 Thread Loris Bennett
Hi Simon, Simon Flood <s.m.fl...@uis.cam.ac.uk> writes: > Hi Loris, > > On 27/04/18 13:46, Loris Bennett wrote: >> Hi, >> >> If I dump my account structure with sacctmgr, I get >> >>Parent - 'geowiss' >>Account - 'geochemie':Fairs

Re: [slurm-users] sacctmgr - bug listing accounts?

2018-04-30 Thread Loris Bennett
Hi Ole, Ole Holm Nielsen <ole.h.niel...@fysik.dtu.dk> writes: > Hi Loris, > > On 04/30/2018 10:12 AM, Loris Bennett wrote: >> Thanks, I should have spotted that, although I don't understand the >> difference between 'parent' and 'organisation' and in fact asked this

Re: [slurm-users] How to short work folder in `squeue`

2018-01-09 Thread Loris Bennett
in online. > > Is there any way to shorten the $HOME to ~? > > Thanks in advance. It's a bit of a hack, but how about squeue -u $(whoami) -o "%.10i %.10P %.20j %.2t %.10M %.9l %.6D %R %Z" | sed -e 's%/home/[^/]\+/*%~/%' ? Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Fr

Re: [slurm-users] Slurm and available libraries

2018-01-17 Thread Loris Bennett
his is all very OT, so it might be better to discuss it on, say, the OpenHPC mailing list, since as far as I can tell Spack, EasyBuild and Lmod (but not old or new 'environment-modules') are part of OpenHPC. Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

[slurm-users] Overiding job QOS limit for individual user?

2018-01-16 Thread Loris Bennett
, the above command has no effect, because the job QOS limit has a higher precedence than the association limit. Is there another way to temporarily limit the number of jobs for an individual user? Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu

[slurm-users] Requirement to use QOS?

2018-01-19 Thread Loris Bennett
anyone confirm this? Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Requirement to use QOS?

2018-01-22 Thread Loris Bennett
Loris Bennett <loris.benn...@fu-berlin.de> writes: > Hi, > > Some while ago I defined several QOS thus: > > Name Priority MaxWall MaxJobs MaxSubmit > -- -- --- --- - > normal 0

Re: [slurm-users] More cores than on one node

2018-01-17 Thread Loris Bennett
e possible. Have you tried? If so, do you get an error? Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] More cores than on one node

2018-01-18 Thread Loris Bennett
ou probably want srun --ntasks=17 --pty bash I'd suggest you use the long forms of the options until you get more familiar with Slurm (although even that can still be confusing, cf. core/cpu, task/process). Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Creating priority quotas

2018-01-25 Thread Loris Bennett
all jobs on that > node when a "VIP" uses the queue. > > We are using SSSD for our authentication system to the login node. > > I'm looking at the QOS docs and am stumped. > > Any help or direction much appreciated. > > Brian Novogradac > > -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Requirement to use QOS?

2018-01-29 Thread Loris Bennett
Loris Bennett <loris.benn...@fu-berlin.de> writes: > Loris Bennett <loris.benn...@fu-berlin.de> writes: > >> Hi, >> >> Some while ago I defined several QOS thus: >> >> Name Priority MaxWall MaxJobs MaxSubmit >> -- -

[slurm-users] Is QOS always inherited explicitly?

2018-02-06 Thread Loris Bennett
inherited). In this case, will a new association added within this hierarchy automatically be associated with the QOS available to the other associations? Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Set priority without sudo and without a database ?

2018-02-12 Thread Loris Bennett
Fabien ELOY <eloy.polyt...@gmail.com> writes: >> 2018-02-12 11:51 GMT+01:00 Loris Bennett <loris.benn...@fu-berlin.de>: >> >> Hi Fabien, >> >> Fabien ELOY <eloy.polyt...@gmail.com> writes: >> >> > Hello, >> > >>

Re: [slurm-users] Set priority without sudo and without a database ?

2018-02-12 Thread Loris Bennett
much as possible. You probably what to look at QOS. This would allow you to, say, define a high-priority QOS which had a priority bonus but also limit on how many cores per user can uses the QOS. That way Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] slurmstepd: error: Exceeded job memory limit at some point.

2018-02-14 Thread Loris Bennett
ackoverflow. Does anyone know what is > happening here? Maybe once in a while a simulation really does just use more memory than you were expecting. Have a look at the output of sacct -j 123456 -o jobid,maxrss,state --units=M with the appropriate job ID. Regards Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Allocate more memory

2018-02-07 Thread Loris Bennett
un on more than one node, e.g. is MPI enabled. Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Allocate more memory

2018-02-07 Thread Loris Bennett
Loris Bennett <loris.benn...@fu-berlin.de> writes: > Hi David, > > david martin <vila...@gmail.com> writes: > >>  >> >> Hi, >> >> I would like to submit a job that requires 3Go. The problem is that I have >> 70 nodes available eac

Re: [slurm-users] Allocate more memory

2018-02-07 Thread Loris Bennett
array 1-10%10:1 >> >> #SBATCH mem-per-cpu=3000m >> >> srun R CMD BATCH myscript.R >> >> >> >> thanks >> >> >> >> >> On 07/02/2018 15:50, Loris Bennett wrote: >>> Hi David, >>> >>> david ma

Re: [slurm-users] How to deal with user running stuff in frontend node?

2018-02-15 Thread Loris Bennett
are set up. We have also had problems automating the restart of the two daemons affected, so it is not that elegant a solution. However it works for us as we only set up a few new users a week. Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] ntasks and cpus-per-task

2018-02-22 Thread Loris Bennett
e downside of my approach is that if the user forgets to specify --nodes and --ntasks is greater than 1, non-MPI jobs can be assigned to multiple nodes. Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Odd behavior/bug with --array env SLURM_ARRAY_TASK_MAX

2018-02-19 Thread Loris Bennett
ot;. This definition of SLURM_ARRAY_TASK_MAX seems like it would definitely be useful. What is the use case for what you expected? Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] ntasks and cpus-per-task

2018-02-22 Thread Loris Bennett
, but maybe we should indeed be getting the users to use multiple CPUs with a single task. Thanks for the info. Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] ntasks and cpus-per-task

2018-02-23 Thread Loris Bennett
ng run 8 times with all of them writing to the same log and output files. Is ORCA just a pathological exception to the idea that it's always good to use 'srun'? (As it causes well over 95% of our affinity problems, it is already pathological in that sense.) Cheers, Loris Footnotes: [1] https

Re: [slurm-users] ntasks and cpus-per-task

2018-02-22 Thread Loris Bennett
they should forget about multiple tasks and just set --tasks-per-cpu for the default 1 task. That way I wouldn't get users running a single-threaded application on 100 cores (the 1000-core job got stuck in the queue :-/ ). I think I'm convinced. Cheers, Loris [snip (53 lines)] -- Dr.

Re: [slurm-users] Transparently assign different walltime limit to a group of nodes ?

2018-08-13 Thread Loris Bennett
ging anything else and have only > jobs with walltime <1day on thiese nodes in the beginning. If you just want to reduce the allowed wall-time for a given rack, can't you just use a maintenance reservation for the appropriate set of nodes? Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

[slurm-users] Job reordering for users?

2018-03-14 Thread Loris Bennett
on my part or does something along those lines exist? Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Job reordering for users?

2018-03-14 Thread Loris Bennett
e man page is only partially updated. > > We don't use this at our center, but thought I'd look into it if we > change our policy. Thanks, Jessica, this was I was thinking of. Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] User limits

2018-03-15 Thread Loris Bennett
acctmgr list assoc format=account,user,maxwall user=mahmood Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Python code for munging hostfiles

2018-04-17 Thread Loris Bennett
g Plan (TM) to recode it in Julia, for no real reason > other than curiosity. > Are you thinking of 'hostnames': $ scontrol show hostnames node[1-3] node1 node2 node3 Good luck with the CP! Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Python code for munging hostfiles

2018-04-17 Thread Loris Bennett
Loris Bennett <loris.benn...@fu-berlin.de> writes: > Hi John, > > John Hearns <hear...@googlemail.com> writes: > >> Please can some kind soul remind me what the Python code for mangling >> Slurm and PBS machinefiles is called please? We discussed it here

Re: [slurm-users] Way MaxRSS should be interpreted

2018-04-17 Thread Loris Bennett
d then remembering that I have already worked out how it was supposed to be interpreted. My suggestion for improving this would be "Maximum individual resident set size of all resident set sizes associated with the tasks in job." It's a little clunky, but I hope it is clearer. Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Slurm overhead

2018-04-20 Thread Loris Bennett
o the node. This means that the elapsed time also includes the time for the node to be provisioned. If this is not relevant in your case, then you are probably just not comparing like with like, e.g. is the hardware underlying /tmp identical in both cases? Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Problem with assigning user to partition

2018-04-19 Thread Loris Bennett
o read https://slurm.schedmd.com/accounting.html and then set up accounts and associations as required. Regards Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Problem with assigning user to partition

2018-04-20 Thread Loris Bennett
set partition=MONTHLY1 > Unknown option: partition=MONTHLY1 > Use keyword 'where' to modify condition I thinks the option should be 'partitions', plural. -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Problem with assigning user to partition

2018-04-20 Thread Loris Bennett
reate a user, but you can't change it later using 'modify' as it is then only a 'where option'. So it looks to me like you need to delete your user and recreate it with the desired partition. Cheers, Loris PS: In your example you have a typo: MONTHLLY1 with double 'L' - don't let that trip you up. --

Re: [slurm-users] Problem with assigning user to partition

2018-04-20 Thread Loris Bennett
le thinking about how to automate the process. Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Problem with assigning user to partition

2018-04-20 Thread Loris Bennett
> Because you can set it with 'add user', but as you can see from the above (from 'sacctmgr -h'), 'modify user' distinguishes between 'set options' and 'where options'. 'Partitions' is a 'where option'. Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] scontrol: can't hold by jobname

2018-03-19 Thread Loris Bennett
> https://github.com/SchedMD/slurm/blob/master/src/scontrol/update_job.c) > > On Mon, Mar 19, 2018 at 9:17 AM, Loris Bennett <loris.benn...@fu-berlin.de> > wrote: > > Hi, > > The manpage for version 17.02.9 of 'scontrol' says the following about > the argument for '

[slurm-users] scontrol: can't hold by jobname

2018-03-19 Thread Loris Bennett
However, I can't get the syntax right. scontrol hold jobname=g09 scontrol hold jobname="g09" scontrol hold "jobname=g09" all give me the error: Invalid job id specified for job jobname=g09 slurm_suspend error: Invalid job id specified Does anyone know what I am doing wrong

Re: [slurm-users] #SBATCH options as Bash script parameters

2018-03-19 Thread Loris Bennett
rror file directories) into > externally defined script parameters (e.g. in the same command line as > during sbatch job submission). Maybe I am misunderstanding your question, but isn't sbatch --time 01:00:00 --mem=1024M --output=out.txt --error=err.txt what you want? Cheers, Loris -- Dr. Loris

[slurm-users] sacctmgr - Use-case for 'Organisation' != 'Parent'

2018-04-26 Thread Loris Bennett
assume 'Organisation' could be used to set up cross-departmental groups, but in my situation that doesn't seem particularly useful. Could anyone who uses 'Organisation' briefly explain his/her use-case? Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email

Re: [slurm-users] how to easily to obtain jobid for array jobs?

2018-10-11 Thread Loris Bennett
s will have a unique value for each ele‐ > ment of job arrays. (Valid for jobs only) You could always just use overwrite squeue with alias which you put it in /etc/profile.d or where ever you have your global setting, although this could also potentially cause some confusio

Re: [slurm-users] Create users

2018-09-13 Thread Loris Bennett
t; sacctmgr create user jdoe account=test > > Also, is there anyway of creating a user at login node and replicate to the > compute nodes ? What is the best practice for user creation ? > > Thanks in advance > > -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Users able to submit jobs when they don't exist

2018-09-14 Thread Loris Bennett
it" approach Paul Edmon describes also seems interesting. Cheers, Loris > Thanks for your input. > > Tim. > > [1] - > https://github.com/SchedMD/slurm/blob/5eea178ddad47c55007e32c08a89d89bd783ebad/src/slurmd/job.c#L108 -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] How to set priorities of actual obs

2018-09-14 Thread Loris Bennett
> Ketiw I'm not aware that this is possible. What would be the use-case for this? Normally you would want a job to make full use of any cores it had reserved. Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] How to set priorities of actual obs

2018-09-14 Thread Loris Bennett
kesim writes: >> On Fri, Sep 14, 2018 at 2:41 PM Loris Bennett >> wrote: >> >> Hi Ketiw, >> >> kesim writes: >> >> > Dear all, >> > >> > I would like to submit a job in such a way that the actual program is >&

Re: [slurm-users] Slurm 18.08 X11 Errors

2018-09-16 Thread Loris Bennett
> [NB] : x2go -> [SLS] : srun --pty bash -> [SNS] : export DISPLAY=[SLS]:50 ; > xeyes > OK > > {same behaviour as X2go for VNC.} > > Any hints please ? > > Thanks, > Luca > -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Slurm Accounting Question

2018-11-20 Thread Loris Bennett
n storing it outside of Slurm's standard accounting. Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Excessive use of backfill on a cluster

2018-11-20 Thread Loris Bennett
is how backfilling is supposed to work. Or am I misunderstanding your problem? Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de

Re: [slurm-users] Excessive use of backfill on a cluster

2018-11-20 Thread Loris Bennett
on = 0 > PriorityWeightQOS = 100 > PriorityWeightTRES = (null) > PropagatePrioProcess = 0 > > ---------- > From: Loris Bennett > Sent: 20 November 2018 13:26:14 > To: Baker D.J. > Cc: Slurm User Community List > Subject: Re: [slurm-users] Excessive use of backfill on a cl

Re: [slurm-users] possible to set memory slack space before killing jobs?

2018-12-05 Thread Loris Bennett
r me to be more accurate in future. In fact, I may be rewarded for requesting too little RAM, since jobs requesting fewer resources may tend to start earlier. Cheers, Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email loris.benn...@fu-berlin.de