Good catch. I didn't even notice that. I definitely think that is
ntpd.conf file on the head node is restricting access by IP range.
Prentice
On 10/28/20 3:04 AM, Williams, Gareth (IM&T, Black Mountain) wrote:
I’m pretty sure that ntp info indicates ntp is not working. reach=0 so
no successf
Having the head node run as an NTP server is a good idea. I set up my
clusters the same way. Is it possible that ntp.conf on the head node has
a restrict statement that restricts access to it by IP address/range,
which is why this one node on a different network can't reach it?
It sounds like
That is interesting as I run with SElinux enforcing.
I will do some more testing of attaching by ssh to nodes with running jobs.
William
On Thu, 29 Oct 2020, 11:58 Paul Raines, wrote:
> The debugging was useful. The problem turned out to be that I am running
> with SELINUX enabled due to corp
Interesting...
On Thu, Oct 29, 2020 at 7:56 AM Paul Raines
wrote:
> The debugging was useful. The problem turned out to be that I am running
> with SELINUX enabled due to corporate policy. The issue was SELINUX is
> blocking sshd access to /var/slurm/spool/d socket files:
>
> time->Thu Oct 29
The debugging was useful. The problem turned out to be that I am running
with SELINUX enabled due to corporate policy. The issue was SELINUX is
blocking sshd access to /var/slurm/spool/d socket files:
time->Thu Oct 29 07:53:50 2020
type=AVC msg=audit(1603972430.809:2800): avc: denied { write
Good morning everyone.
I'm having a "issue", I don't know if it is a "bug or a feature".
I've created a QOS: "sacctmgr add qos myqos set GrpTRESMins=cpu=10
flags=NoDecay".
I know the limit it too low, but I just wanted to give you guys an example.
Whenever a user submits a job and uses this Q
Okay, thanks for the hint that I should use cgroups.
With cgroups the behaviour is as expected.
:)
Max
> Il 10/10/20 18:53, Renfro, Michael ha scritto:
>
> > * Do you want to ensure that one job requesting 9 tasks (and 1 CPU per
> > task) cant overstep its reservation and take
