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 +1,60 @@
+---
+- name: Generate measurable Slurm usage for sreport
+  hosts: slurm_controller
+  become: true
+  gather_facts: false
+
+  tasks:
+    - name: Submit CPU usage job
+      ansible.builtin.shell: |
+        set -euo pipefail
+
+        job_id="$(
+          sudo -iu slurmuser sbatch --parsable <<'SBATCH'
+        #!/bin/bash
+        #SBATCH --job-name=sreport-usage
+        #SBATCH --partition=debug
+        #SBATCH --cpus-per-task=2
+        #SBATCH --mem=512M
+        #SBATCH --time=00:03:00
+        #SBATCH --output=/shared/sreport-usage-%j.out
+
+        echo "HOST=$(hostname)"
+        echo "SLURM_JOB_ID=$SLURM_JOB_ID"
+        echo "SLURM_CPUS_PER_TASK=${SLURM_CPUS_PER_TASK:-}"
+        echo "CPUS_ALLOWED=$(grep Cpus_allowed_list /proc/self/status)"
+        echo "Burning CPU for 90 seconds"
+
+        timeout 90 bash -c 'while true; do :; done' &
+        timeout 90 bash -c 'while true; do :; done' &
+        wait
+
+        echo "Done"
+        date
+        SBATCH
+        )"
+
+        echo "JOB_ID=$job_id"
+
+        for i in $(seq 1 150); do
+          if squeue -h -j "$job_id" | grep -q .; then
+            squeue -j "$job_id"
+            sleep 2
+          else
+            break
+          fi
+        done
+
+        echo "### sacct"
+        sacct -j "$job_id" --format=JobID,JobName,User,Partition,State,ExitCode,Elapsed,AllocCPUS,ReqMem,NodeList
+
+        echo "### output"
+        cat "/shared/sreport-usage-${job_id}.out"
+      args:
+        executable: /bin/bash
+      register: sreport_usage_job
+      changed_when: true
+
+    - name: Show usage job result
+      ansible.builtin.debug:
+        var: sreport_usage_job.stdout_lines