[slurm-users] [External] Hibernating a whole cluster

Diego Zuccato diego.zuccato at unibo.it
Tue Feb 7 13:55:46 UTC 2023


That's probably not optimal, but could work. I'd go with brutal 
preemption: swapping 90+G can be quite time-consuming.

Diego

Il 07/02/2023 14:18, Analabha Roy ha scritto:
> 
> 
> On Tue, 7 Feb 2023, 18:12 Diego Zuccato, <diego.zuccato at unibo.it 
> <mailto:diego.zuccato at unibo.it>> wrote:
> 
>     RAM used by a suspended job is not released. At most it can be swapped
>     out (if enough swap is available).
> 
> 
> 
> There should be enough swap available. I have 93 gigs of Ram and as big 
> a swap partition. I can top it off with swap files if needed.
> 
> 
> 
> 
> 
>     Il 07/02/2023 13:14, Analabha Roy ha scritto:
>      > Hi Sean,
>      >
>      > Thanks for your awesome suggestion! I'm going through the
>     reservation
>      > docs now. At first glance, it seems like a daily reservation
>     would turn
>      > down jobs that are too big for the reservation. It'd be nice if
>      > slurm could suspend (in the manner of 'scontrol suspend') jobs
>     during
>      > reserved downtime and resume them after. That way, folks can submit
>      > large jobs without having to worry about the downtimes. Perhaps
>     the FLEX
>      > option in reservations can accomplish this somehow?
>      >
>      >
>      > I suppose that I can do it using a shell script iterator and a
>     cron job,
>      > but that seems like an ugly hack. I was hoping if there is a way to
>      > config this in slurm itself?
>      >
>      > AR
>      >
>      > On Tue, 7 Feb 2023 at 16:06, Sean Mc Grath <smcgrat at tcd.ie
>     <mailto:smcgrat at tcd.ie>
>      > <mailto:smcgrat at tcd.ie <mailto:smcgrat at tcd.ie>>> wrote:
>      >
>      >     Hi Analabha,
>      >
>      >     Could you do something like create a daily reservation for 8
>     hours
>      >     that starts at 9am, or whatever times work for you like the
>      >     following untested command:
>      >
>      >     scontrol create reservation starttime=09:00:00 duration=8:00:00
>      >     nodecnt=1 flags=daily ReservationName=daily
>      >
>      >     Daily option at
>     https://slurm.schedmd.com/scontrol.html#OPT_DAILY
>     <https://slurm.schedmd.com/scontrol.html#OPT_DAILY>
>      >     <https://slurm.schedmd.com/scontrol.html#OPT_DAILY
>     <https://slurm.schedmd.com/scontrol.html#OPT_DAILY>>
>      >
>      >     Some more possible helpful documentation at
>      > https://slurm.schedmd.com/reservations.html
>     <https://slurm.schedmd.com/reservations.html>
>      >     <https://slurm.schedmd.com/reservations.html
>     <https://slurm.schedmd.com/reservations.html>>, search for "daily".
>      >
>      >     My idea being that jobs can only run in that reservation, (that
>      >     would have to be configured separately, not sure how from the
>     top of
>      >     my head), which is only active during the times you want the
>     node to
>      >     be working. So the cronjob that hibernates/shuts it down will
>     do so
>      >     when there are no jobs running. At least in theory.
>      >
>      >     Hope that helps.
>      >
>      >     Sean
>      >
>      >     ---
>      >     Sean McGrath
>      >     Senior Systems Administrator, IT Services
>      >
>      >   
>       ------------------------------------------------------------------------
>      >     *From:* slurm-users <slurm-users-bounces at lists.schedmd.com
>     <mailto:slurm-users-bounces at lists.schedmd.com>
>      >     <mailto:slurm-users-bounces at lists.schedmd.com
>     <mailto:slurm-users-bounces at lists.schedmd.com>>> on behalf of
>      >     Analabha Roy <hariseldon99 at gmail.com
>     <mailto:hariseldon99 at gmail.com> <mailto:hariseldon99 at gmail.com
>     <mailto:hariseldon99 at gmail.com>>>
>      >     *Sent:* Tuesday 7 February 2023 10:05
>      >     *To:* Slurm User Community List
>     <slurm-users at lists.schedmd.com <mailto:slurm-users at lists.schedmd.com>
>      >     <mailto:slurm-users at lists.schedmd.com
>     <mailto:slurm-users at lists.schedmd.com>>>
>      >     *Subject:* Re: [slurm-users] [External] Hibernating a whole
>     cluster
>      >     Hi,
>      >
>      >     Thanks. I had read the Slurm Power Saving Guide before. I believe
>      >     the configs enable slurmctld to check other nodes for
>     idleness and
>      >     suspend/resume them. Slurmctld must run on a separate, always-on
>      >     server for this to work, right?
>      >
>      >     My issue might be a little different. I literally have only
>     one node
>      >     that runs everything: slurmctld, slurmd, slurmdbd, everything.
>      >
>      >     This node must be set to "sudo systemctl hibernate"after business
>      >     hours, regardless of whether jobs are queued or running. The next
>      >     business day, it can be switched on manually.
>      >
>      >     systemctl hibernate is supposed to save the entire run state
>     of the
>      >     sole node to swap and poweroff. When powered on again, it should
>      >     restore everything to its previous running state.
>      >
>      >     When the job queue is empty, this works well. I'm not sure
>     how well
>      >     this hibernate/resume will work with running jobs and would
>      >     appreciate any suggestions or insights.
>      >
>      >     AR
>      >
>      >
>      >     On Tue, 7 Feb 2023 at 01:39, Florian Zillner
>     <fzillner at lenovo.com <mailto:fzillner at lenovo.com>
>      >     <mailto:fzillner at lenovo.com <mailto:fzillner at lenovo.com>>> wrote:
>      >
>      >         Hi,
>      >
>      >         follow this guide:
>     https://slurm.schedmd.com/power_save.html
>     <https://slurm.schedmd.com/power_save.html>
>      >         <https://slurm.schedmd.com/power_save.html
>     <https://slurm.schedmd.com/power_save.html>>
>      >
>      >         Create poweroff / poweron scripts and configure slurm to
>     do the
>      >         poweroff after X minutes. Works well for us. Make sure to
>     set an
>      >         appropriate time (ResumeTimeout) to allow the node to
>     come back
>      >         to service.
>      >         Note that we did not achieve good power saving with
>     suspending
>      >         the nodes, powering them off and on saves way more power. The
>      >         downside is it takes ~ 5 mins to resume (= power on) the
>     nodes
>      >         when needed.
>      >
>      >         Cheers,
>      >         Florian
>      >       
>       ------------------------------------------------------------------------
>      >         *From:* slurm-users
>     <slurm-users-bounces at lists.schedmd.com
>     <mailto:slurm-users-bounces at lists.schedmd.com>
>      >         <mailto:slurm-users-bounces at lists.schedmd.com
>     <mailto:slurm-users-bounces at lists.schedmd.com>>> on behalf of
>      >         Analabha Roy <hariseldon99 at gmail.com
>     <mailto:hariseldon99 at gmail.com>
>      >         <mailto:hariseldon99 at gmail.com
>     <mailto:hariseldon99 at gmail.com>>>
>      >         *Sent:* Monday, 6 February 2023 18:21
>      >         *To:* slurm-users at lists.schedmd.com
>     <mailto:slurm-users at lists.schedmd.com>
>      >         <mailto:slurm-users at lists.schedmd.com
>     <mailto:slurm-users at lists.schedmd.com>>
>      >         <slurm-users at lists.schedmd.com
>     <mailto:slurm-users at lists.schedmd.com>
>      >         <mailto:slurm-users at lists.schedmd.com
>     <mailto:slurm-users at lists.schedmd.com>>>
>      >         *Subject:* [External] [slurm-users] Hibernating a whole
>     cluster
>      >         Hi,
>      >
>      >         I've just finished  setup of a single node "cluster" with
>     slurm
>      >         on ubuntu 20.04. Infrastructural limitations  prevent me from
>      >         running it 24/7, and it's only powered on during
>     business hours.
>      >
>      >
>      >         Currently, I have a cron job running that hibernates that
>     sole
>      >         node before closing time.
>      >
>      >         The hibernation is done with standard systemd, and
>     hibernates to
>      >         the swap partition.
>      >
>      >           I have not run any lengthy slurm jobs on it yet. Before
>     I do,
>      >         can I get some thoughts on a couple of things?
>      >
>      >         If it hibernated when slurm still had jobs
>     running/queued, would
>      >         they resume properly when the machine powers back on?
>      >
>      >         Note that my swap space is bigger than my  RAM.
>      >
>      >         Is it necessary to perhaps setup a pre-hibernate script for
>      >         systemd to  iterate scontrol to suspend all the jobs before
>      >         hibernating and resume them post-resume?
>      >
>      >         What about the wall times? I'm uessing that slurm will
>     count the
>      >         downtime as elapsed for each job. Is there a way to
>     config this,
>      >         or is the only alternative a post-hibernate script that
>      >         iteratively updates the wall times of the running jobs using
>      >         scontrol again?
>      >
>      >         Thanks for your attention.
>      >         Regards
>      >         AR
>      >
>      >
>      >
>      >     --
>      >     Analabha Roy
>      >     Assistant Professor
>      >     Department of Physics
>      >     <http://www.buruniv.ac.in/academics/department/physics
>     <http://www.buruniv.ac.in/academics/department/physics>>
>      >     The University of Burdwan <http://www.buruniv.ac.in/
>     <http://www.buruniv.ac.in/>>
>      >     Golapbag Campus, Barddhaman 713104
>      >     West Bengal, India
>      >     Emails: daneel at utexas.edu <mailto:daneel at utexas.edu>
>     <mailto:daneel at utexas.edu <mailto:daneel at utexas.edu>>,
>      > aroy at phys.buruniv.ac.in <mailto:aroy at phys.buruniv.ac.in>
>     <mailto:aroy at phys.buruniv.ac.in <mailto:aroy at phys.buruniv.ac.in>>,
>      > hariseldon99 at gmail.com <mailto:hariseldon99 at gmail.com>
>     <mailto:hariseldon99 at gmail.com <mailto:hariseldon99 at gmail.com>>
>      >     Webpage: http://www.ph.utexas.edu/~daneel/
>     <http://www.ph.utexas.edu/~daneel/>
>      >     <http://www.ph.utexas.edu/~daneel/
>     <http://www.ph.utexas.edu/~daneel/>>
>      >
>      >
>      >
>      > --
>      > Analabha Roy
>      > Assistant Professor
>      > Department of Physics
>      > <http://www.buruniv.ac.in/academics/department/physics
>     <http://www.buruniv.ac.in/academics/department/physics>>
>      > The University of Burdwan <http://www.buruniv.ac.in/
>     <http://www.buruniv.ac.in/>>
>      > Golapbag Campus, Barddhaman 713104
>      > West Bengal, India
>      > Emails: daneel at utexas.edu <mailto:daneel at utexas.edu>
>     <mailto:daneel at utexas.edu <mailto:daneel at utexas.edu>>,
>      > aroy at phys.buruniv.ac.in <mailto:aroy at phys.buruniv.ac.in>
>     <mailto:aroy at phys.buruniv.ac.in <mailto:aroy at phys.buruniv.ac.in>>,
>      > hariseldon99 at gmail.com <mailto:hariseldon99 at gmail.com>
>     <mailto:hariseldon99 at gmail.com <mailto:hariseldon99 at gmail.com>>
>      > Webpage: http://www.ph.utexas.edu/~daneel/
>     <http://www.ph.utexas.edu/~daneel/>
>      > <http://www.ph.utexas.edu/~daneel/
>     <http://www.ph.utexas.edu/~daneel/>>
> 
>     -- 
>     Diego Zuccato
>     DIFA - Dip. di Fisica e Astronomia
>     Servizi Informatici
>     Alma Mater Studiorum - Università di Bologna
>     V.le Berti-Pichat 6/2 - 40127 Bologna - Italy
>     tel.: +39 051 20 95786
> 

-- 
Diego Zuccato
DIFA - Dip. di Fisica e Astronomia
Servizi Informatici
Alma Mater Studiorum - Università di Bologna
V.le Berti-Pichat 6/2 - 40127 Bologna - Italy
tel.: +39 051 20 95786



More information about the slurm-users mailing list