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 +1,40 @@
+---
+- name: Discover node resources for Slurm config
+  hosts: slurm_cluster
+  become: true
+  gather_facts: true
+
+  tasks:
+    - name: Discover CPU and memory
+      ansible.builtin.shell: |
+        set -euo pipefail
+        echo "HOST={{ inventory_hostname }}"
+        echo "CPUS=$(nproc)"
+        echo "REAL_MEMORY_MB=$(awk '/MemTotal/ {print int($2/1024)}' /proc/meminfo)"
+        echo "SOCKETS=$(lscpu | awk -F: '/Socket\\(s\\)/ {gsub(/ /,\"\",$2); print $2}')"
+        echo "CORES_PER_SOCKET=$(lscpu | awk -F: '/Core\\(s\\) per socket/ {gsub(/ /,\"\",$2); print $2}')"
+        echo "THREADS_PER_CORE=$(lscpu | awk -F: '/Thread\\(s\\) per core/ {gsub(/ /,\"\",$2); print $2}')"
+      args:
+        executable: /bin/bash
+      register: cpu_mem
+      changed_when: false
+
+    - name: Discover NVIDIA GPU if present
+      ansible.builtin.shell: |
+        set -euo pipefail
+        if command -v nvidia-smi >/dev/null 2>&1; then
+          nvidia-smi --query-gpu=index,name,memory.total --format=csv,noheader
+        else
+          echo "NO_NVIDIA_SMI"
+        fi
+      args:
+        executable: /bin/bash
+      register: gpu_info
+      changed_when: false
+
+    - name: Show discovered resources
+      ansible.builtin.debug:
+        msg:
+          - "{{ cpu_mem.stdout_lines }}"
+          - "GPU:"
+          - "{{ gpu_info.stdout_lines }}"