Add Slurm AI/HPC cluster platform project

2026-06-04 19:41:05 +00:00
parent e2624a7533
commit d300d490f5
49 changed files with 4777 additions and 0 deletions
@@ -0,0 +1,46 @@
+---
+- name: Fetch latest Slurm backups from nodes to pvef
+  hosts: slurm_cluster
+  become: true
+  gather_facts: false
+
+  vars:
+    remote_backup_base: /var/backups/slurm
+    local_backup_base: "{{ playbook_dir }}/../../artifacts/backups"
+
+  tasks:
+    - name: Find latest remote backup directory
+      ansible.builtin.shell: |
+        set -euo pipefail
+        ls -1dt {{ remote_backup_base }}/* | head -n 1
+      args:
+        executable: /bin/bash
+      register: latest_backup_dir
+      changed_when: false
+
+    - name: Create local backup directory on pvef
+      ansible.builtin.file:
+        path: "{{ local_backup_base }}/{{ inventory_hostname }}"
+        state: directory
+        mode: "0700"
+      delegate_to: localhost
+      become: false
+
+    - name: Archive latest backup directory on remote node
+      ansible.builtin.archive:
+        path: "{{ latest_backup_dir.stdout }}"
+        dest: "/tmp/{{ inventory_hostname }}-slurm-backup.tgz"
+        format: gz
+        force_archive: true
+      changed_when: true
+
+    - name: Fetch archive to pvef
+      ansible.builtin.fetch:
+        src: "/tmp/{{ inventory_hostname }}-slurm-backup.tgz"
+        dest: "{{ local_backup_base }}/{{ inventory_hostname }}/"
+        flat: true
+
+    - name: Remove temporary remote archive
+      ansible.builtin.file:
+        path: "/tmp/{{ inventory_hostname }}-slurm-backup.tgz"
+        state: absent