Just to add, squeue returns
JOBID PARTITION NAME USER ST TIME NODES
NODELIST(REASON)
7 standard hostname ubuntu R 0:21 1 node0
James Venning
On 31 August 2016 at 12:57, James Andrew Venning wrote:
> Hi all again,
>
Hi all again,
Initial problems are fixed, but there are more - thanks in advance for
reading this!
Ubuntu 14.04 with Slurm 2.6.5-1
Master and controller seem to be talking to each other:
scontrol ping
Slurmctld(primary/backup) at slurm-master/(NULL) are UP/DOWN
exact same message from each slave
On 31/08/16 10:35, James Andrew Venning wrote:
> slurmctld: error: this host (slurm-master) not valid controller
> (144.6.230.71 or (null))
That looks like the main issue, for some reason Slurm doesn't think it's
running on the node you want it to.
> As an aside, I installed with sudo apt-get
On 30/08/16 22:11, Manuel Rodríguez Pascual wrote:
> We hope that this can be useful for the Slurm community.
That's really pretty neat!
I can't test myself as we're stuck on RHEL6 for the moment but I do
wonder if you've considered doing the same for Open-MPI so that Slurm
can do
Dear Slurm-Dev Admin,
In Ubuntu 16.04LTS, Slurmdbd (v15.08.7) [1] will not run when running
mysql-client (v5.7.13) [2] (both packages are from the Ubuntu repo). This
is because MySQL v5.7.13 does not support the "IGNORE" clause when it is
used with "ALTER" [3], and Slurmdbd attempts to ALTER
Thanks for the suggestions guys. I fixed one of my problems (wrong IP
address for the master - duh), but still can't get it to run. I'm on Ubuntu
14.04, slurm version is 2.6.5-1.
When I run sudo slurmctld -Dvvv, I get
slurmctld: pidfile not locked, assuming no running daemon
slurmctld: error:
Hi all,
After working together with CRIU ( https://criu.org/Main_Page )
developers, my team at CIEMAT has developed a CRIU plugin from Slurm.
This way, Slurm can employ this checkpoint/restart library to perform
these operations.
It is stored in my personal github account,
Am Tue, 30 Aug 2016 03:12:54 -0700
schrieb Bjørn-Helge Mevik :
> handler for the EXIT "signal", which prints out resource usage.
This is an idea, indeed. But users might get the idea to install a
handler themselves for cleanup tasks. On the other hand, since we
indeed urge
Maybe you can create a partition/qos for interactive jobs and use
job_submit plugin to force all interactive jobs to use it?
cheers,
Marcin
2016-08-30 8:09 GMT+02:00 John Hearns :
> I worked on the same problem in my last job, where engineers had
> interactive sessions
"Dr. Thomas Orgis" writes:
> Am Sun, 21 Aug 2016 17:29:39 -0700
> schrieb Christopher Samuel :
>
>> Unfortunately you can only do this as part of the taskprolog, so
>> prepending to the users stdout.
>
> Thanks for confirming the (for me)
Hi,
I didn't see an answer so far, so I try to reason:
On 08/29/2016 19:40, Luis Torres wrote:
> We have recently deployed SLURM v 15.08.7-build1 on Ubuntu 16.04
> submission and execution nodes with apt-get; we built and installed the
> source packages of the same release on Ubuntu 14.04 for
Re: [slurm-dev] Re: SLURM daemon doesn't start
I fix the systemctl dameon with Centos 7.2 add
After=network.target slurmdbd.service
ConditionPathExists=/etc/slurm/slurm.conf
On /usr/lib/systemd/system/slurmctld.service
And now Works fine
*DAVID RAMIREZ *
HPC
Just run slurmctld into the foreground, check the output. If you still
don't know the cause of the problem paste a few lines here.
cheers,
Marcin
James,
Would be great to know OS and SLURM version.
For instance, on Centos 7/Debian 8/Ubuntu 16.04, you might be using
systemctl status/start/restart slurmctld (head node)
systemctl status/start/restart slurmd (worker nodes)
instead?
Cheers
L.
--
The most dangerous phrase in the
Hi all,
I'm trying to set up a slurm system. I've been through the installation
instructions, but I'm getting stuck on launching the daemon. If I run, from
the slurm controller,
scontrol ping
it informs me:
Slurmctld(primary/backup) at 130.56.254.79/(NULL) are DOWN/DOWN
If I run it as sudo I
15 matches
Mail list logo