Add Slurm AI/HPC cluster platform project

This commit is contained in:
Mateusz Suski
2026-06-04 19:41:05 +00:00
parent e2624a7533
commit cd6830334b
47 changed files with 4727 additions and 0 deletions
@@ -0,0 +1,33 @@
---
- name: Show Slurm node state
hosts: slurm_controller
become: true
gather_facts: false
tasks:
- name: Require target_node
ansible.builtin.fail:
msg: "Use: ansible-playbook show-slurm-node.yml -e target_node=<hostname>"
when: target_node is not defined
- name: Show node state
ansible.builtin.shell: |
set -euo pipefail
echo "### sinfo"
sinfo -N -n {{ target_node }} || true
echo
echo "### scontrol"
scontrol show node {{ target_node }} || true
echo
echo "### jobs on node"
squeue -w {{ target_node }} || true
args:
executable: /bin/bash
register: node_lifecycle_state
changed_when: false
- name: Print node lifecycle state
ansible.builtin.debug:
var: node_lifecycle_state.stdout_lines