Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
H
HPCasCode
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Deploy
Releases
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
hpc-team
HPCasCode
Commits
6e4420db
Commit
6e4420db
authored
3 years ago
by
Damien Leong
Browse files
Options
Downloads
Patches
Plain Diff
Remove probe for GRES/CPU on gpu nodes, and remove gres.conf & slurm.conf, going configless
parent
a74343ea
No related branches found
Branches containing commit
No related tags found
1 merge request
!454
Remove probe for GRES/CPU on gpu nodes, and remove gres.conf & slurm.conf, going configless
Changes
2
Pipelines
1
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
roles/slurm-common/tasks/main.yml
+0
-29
0 additions, 29 deletions
roles/slurm-common/tasks/main.yml
roles/slurm-start/templates/slurmd.service.j2
+3
-2
3 additions, 2 deletions
roles/slurm-start/templates/slurmd.service.j2
with
3 additions
and
31 deletions
roles/slurm-common/tasks/main.yml
+
0
−
29
View file @
6e4420db
...
@@ -118,32 +118,12 @@
...
@@ -118,32 +118,12 @@
-
include
:
createSlurmDirectories.yml
-
include
:
createSlurmDirectories.yml
-
name
:
check slurm generic resource
shell
:
"
{{
slurm_gres_check
}}"
register
:
slurm_generic_resource
ignore_errors
:
true
when
:
slurm_gres_check is defined
check_mode
:
no
changed_when
:
False
-
name
:
Gres - Test for Nvidia devices
script
:
scripts/nvidia-probe.py
register
:
probeOutput
check_mode
:
no
changed_when
:
False
-
name
:
get cpu count
-
name
:
get cpu count
shell
:
'
lscpu
|
grep
"On-line
CPU"
|
cut
-f
2
-d
":"
|
sed
"s/\
*//g"'
shell
:
'
lscpu
|
grep
"On-line
CPU"
|
cut
-f
2
-d
":"
|
sed
"s/\
*//g"'
register
:
cpucount
register
:
cpucount
check_mode
:
no
check_mode
:
no
changed_when
:
False
changed_when
:
False
-
name
:
"
set
nvidiaprobe
slurm_gres_list"
set_fact
:
"
slurm_gres_list={{
probeOutput.stdout
}}"
-
name
:
template gres.conf file
template
:
src="gres.conf.j2" dest={{ slurm_dir }}/etc/gres.conf mode=644
become
:
true
-
name
:
make slurm prolog dir
-
name
:
make slurm prolog dir
file
:
path=/opt/slurm/etc state=directory mode=755
file
:
path=/opt/slurm/etc state=directory mode=755
...
@@ -158,15 +138,6 @@
...
@@ -158,15 +138,6 @@
template
:
src=slurm.epilog.j2 dest=/opt/slurm/etc/slurm.epilog mode=755
template
:
src=slurm.epilog.j2 dest=/opt/slurm/etc/slurm.epilog mode=755
become
:
true
become
:
true
-
name
:
install slurm.conf
copy
:
src=files/slurm.conf dest={{ slurm_dir }}/etc/slurm.conf
become
:
true
when
:
slurm_use_vpn==False
-
name
:
install slurm.conf
template
:
src=slurm-vpn.conf.j2 dest={{ slurm_dir }}/etc/slurm.conf
become
:
true
when
:
slurm_use_vpn==True
-
name
:
setup envirnment variables
-
name
:
setup envirnment variables
template
:
src=slurm_setup.sh.j2 dest=/etc/profile.d/slurm_setup.sh
template
:
src=slurm_setup.sh.j2 dest=/etc/profile.d/slurm_setup.sh
...
...
This diff is collapsed.
Click to expand it.
roles/slurm-start/templates/slurmd.service.j2
+
3
−
2
View file @
6e4420db
[Unit]
[Unit]
Description=Slurm node daemon
Description=Slurm node daemon
After=network.target
After=network.target
ConditionPathExists={{ slurm_dir }}/etc/slurm.conf
# After Slurm-20.02 (configless), this is not needed
# ConditionPathExists={{ slurm_dir }}/etc/slurm.conf
[Service]
[Service]
Type=forking
Type=forking
KillMode=process
KillMode=process
LimitMEMLOCK=infinity
LimitMEMLOCK=infinity
#EnvironmentFile=/etc/default/slurmd
#EnvironmentFile=/etc/default/slurmd
ExecStart={{ slurm_dir }}/sbin/slurmd
$SLURMD_OPTIONS
ExecStart={{ slurm_dir }}/sbin/slurmd
--conf-server {{ slurmctrl }}:6817
PIDFile={{ slurmpiddir }}/slurmd.pid
PIDFile={{ slurmpiddir }}/slurmd.pid
[Install]
[Install]
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment