Skip to content
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions build/etc/ansible/hosts
Original file line number Diff line number Diff line change
Expand Up @@ -18,3 +18,10 @@ worker-02.cluster

[amd-build]
controller-02.cluster

[slurm-primary]
worker-02.cluster

[slurm-workers]
worker-01.cluster
worker-03.cluster
File renamed without changes.
2 changes: 1 addition & 1 deletion build/etc/slurm-llnl/slurm.conf
Original file line number Diff line number Diff line change
Expand Up @@ -425,4 +425,4 @@ NodeName=worker-03 NodeAddr=100.91.208.123 CPUs=4 State=UNKNOWN
# line where PartitionName is "DEFAULT" will replace or add to previous default
# values and not a reinitialize the default values.

PartitionName=compute-cluster Nodes=worker-[02-03] Default=YES MaxTime=INFINITE State=UP
PartitionName=compute-cluster Nodes=worker-[01-03] Default=YES MaxTime=INFINITE State=UP
98 changes: 89 additions & 9 deletions build/playbooks/slurm/build.yml
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
- name: Build slurm cluster
hosts: arm-build
hosts: slurm-primary
remote_user: pi
tasks:
- name: Install slurm
Expand All @@ -10,13 +10,93 @@
name: 'slurm-wlm'
state: latest
update_cache: yes
- name: Start slurm
- name: Copy munge config
become: yes
become_method: sudo
command: |
systemctl enable munge
systemctl start munge
systemctl enable slurmd
systemctl start slurmd
systemctl enable slurmctld
systemctl start slurmctld
ansible.builtin.copy:
src: /home/blong14/Developer/git/compute-cluster/build/etc/munge/{{item}}
dest: /etc/munge/{{item}}
loop:
- munge.key
- name: Copy slurm config
become: yes
become_method: sudo
ansible.builtin.copy:
src: /home/blong14/Developer/git/compute-cluster/build/etc/slurm-llnl/{{item}}
dest: /etc/slurm/{{item}}
loop:
- cgroup.conf
- cgroup_allowed_devices_file.conf
- plugstack.conf
- slurm.conf
- name: Start munge
become: yes
become_method: sudo
ansible.builtin.systemd:
name: munge
state: started
enabled: true
- name: Start slurmd
become: yes
become_method: sudo
ansible.builtin.systemd:
name: slurmd
state: started
enabled: true
- name: Start slurmctld
become: yes
become_method: sudo
ansible.builtin.systemd:
name: slurmctld
state: started
enabled: true
- name: Build slurm workers
hosts: slurm-workers
remote_user: pi
tasks:
- name: Install slurm
become: yes
become_method: sudo
apt:
name: 'slurmd'
state: latest
update_cache: yes
- name: Install slurm-client
become: yes
become_method: sudo
apt:
name: 'slurm-client'
state: latest
update_cache: yes
- name: Copy munge config
become: yes
become_method: sudo
ansible.builtin.copy:
src: /home/blong14/Developer/git/compute-cluster/build/etc/munge/{{item}}
dest: /etc/munge/{{item}}
loop:
- munge.key
- name: Copy slurm config
become: yes
become_method: sudo
ansible.builtin.copy:
src: /home/blong14/Developer/git/compute-cluster/build/etc/slurm-llnl/{{item}}
dest: /etc/slurm/{{item}}
loop:
- cgroup.conf
- cgroup_allowed_devices_file.conf
- slurm.conf
- name: Start munge
become: yes
become_method: sudo
ansible.builtin.systemd:
name: munge
state: started
enabled: true
- name: Start slurmd
become: yes
become_method: sudo
ansible.builtin.systemd:
name: slurmd
state: started
enabled: true