Add Slurm AI/HPC cluster platform project

2026-06-04 19:41:05 +00:00
parent e2624a7533
commit cd6830334b
47 changed files with 4727 additions and 0 deletions
@@ -0,0 +1,60 @@
+---
+- name: Submit CPU test job
+  hosts: slurm_controller
+  become: true
+  gather_facts: false
+
+  tasks:
+    - name: Submit test job to debug partition
+      ansible.builtin.shell: |
+        set -euo pipefail
+
+        job_id="$(
+          sudo -iu slurmuser sbatch --parsable <<'SBATCH'
+        #!/bin/bash
+        #SBATCH --job-name=cpu-test
+        #SBATCH --partition=debug
+        #SBATCH --cpus-per-task=1
+        #SBATCH --mem=512M
+        #SBATCH --time=00:02:00
+        #SBATCH --output=/shared/cpu-test-%j.out
+
+        echo "HOST=$(hostname)"
+        echo "USER=$(whoami)"
+        echo "SLURM_JOB_ID=$SLURM_JOB_ID"
+        echo "SLURM_JOB_NODELIST=$SLURM_JOB_NODELIST"
+        echo "CPUS_ALLOWED=$(grep Cpus_allowed_list /proc/self/status)"
+        date
+        SBATCH
+        )"
+
+        echo "JOB_ID=$job_id"
+
+        for i in $(seq 1 60); do
+          if sudo -iu slurmuser squeue -h -j "$job_id" | grep -q .; then
+            sudo -iu slurmuser squeue -j "$job_id"
+            sleep 1
+          else
+            break
+          fi
+        done
+
+        echo "### sacct"
+        sudo -iu slurmuser sacct -j "$job_id" --format=JobID,JobName,Partition,State,ExitCode 2>/dev/null || true
+
+        echo "### output"
+        if [ -f "/shared/cpu-test-${job_id}.out" ]; then
+          cat "/shared/cpu-test-${job_id}.out"
+        else
+          echo "Output file not found: /shared/cpu-test-${job_id}.out"
+          find /shared -maxdepth 1 -name "cpu-test-*.out" -ls | tail -5 || true
+          exit 1
+        fi
+      args:
+        executable: /bin/bash
+      register: cpu_job_result
+      changed_when: true
+
+    - name: Show CPU job result
+      ansible.builtin.debug:
+        var: cpu_job_result.stdout_lines