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 +1,105 @@
+---
+- name: Install and configure MariaDB for SlurmDBD
+  hosts: slurm_controller
+  become: true
+  gather_facts: false
+
+  tasks:
+    - name: Install MariaDB and SlurmDBD packages
+      ansible.builtin.apt:
+        name:
+          - mariadb-server
+          - mariadb-client
+          - slurmdbd
+          - slurm-wlm-mysql-plugin
+        state: present
+        update_cache: true
+
+    - name: Ensure MariaDB is enabled and running
+      ansible.builtin.systemd:
+        name: mariadb
+        enabled: true
+        state: started
+
+    - name: Ensure Slurm log directory exists
+      ansible.builtin.file:
+        path: /var/log/slurm
+        state: directory
+        owner: slurm
+        group: slurm
+        mode: "0755"
+
+    - name: Create Slurm accounting database and DB user
+      ansible.builtin.shell: |
+        set -euo pipefail
+        mysql <<SQL
+        CREATE DATABASE IF NOT EXISTS {{ slurmdbd_storage_loc }};
+        CREATE USER IF NOT EXISTS '{{ slurmdbd_storage_user }}'@'localhost' IDENTIFIED BY '{{ slurmdbd_storage_pass }}';
+        CREATE USER IF NOT EXISTS '{{ slurmdbd_storage_user }}'@'127.0.0.1' IDENTIFIED BY '{{ slurmdbd_storage_pass }}';
+        GRANT ALL PRIVILEGES ON {{ slurmdbd_storage_loc }}.* TO '{{ slurmdbd_storage_user }}'@'localhost';
+        GRANT ALL PRIVILEGES ON {{ slurmdbd_storage_loc }}.* TO '{{ slurmdbd_storage_user }}'@'127.0.0.1';
+        FLUSH PRIVILEGES;
+        SQL
+      args:
+        executable: /bin/bash
+      changed_when: true
+
+    - name: Ensure /etc/slurm exists
+      ansible.builtin.file:
+        path: /etc/slurm
+        state: directory
+        owner: root
+        group: root
+        mode: "0755"
+
+    - name: Deploy slurmdbd.conf
+      ansible.builtin.template:
+        src: ../../templates/slurmdbd.conf.j2
+        dest: /etc/slurm/slurmdbd.conf
+        owner: slurm
+        group: slurm
+        mode: "0600"
+      notify:
+        - Restart slurmdbd
+
+    - name: Ensure slurmdbd is enabled and running
+      ansible.builtin.systemd:
+        name: slurmdbd
+        enabled: true
+        state: started
+
+    - name: Flush handlers before validation
+      ansible.builtin.meta: flush_handlers
+
+    - name: Validate slurmdbd service is active
+      ansible.builtin.command:
+        cmd: systemctl is-active slurmdbd
+      register: slurmdbd_active
+      retries: 10
+      delay: 2
+      until: slurmdbd_active.stdout == "active"
+      changed_when: false
+
+    - name: Validate slurmdbd is listening on port
+      ansible.builtin.shell: |
+        set -euo pipefail
+        ss -lntp | grep ':{{ slurmdbd_port }} '
+      args:
+        executable: /bin/bash
+      register: slurmdbd_port_check
+      retries: 10
+      delay: 2
+      until: slurmdbd_port_check.rc == 0
+      changed_when: false
+
+    - name: Show slurmdbd service validation
+      ansible.builtin.debug:
+        msg:
+          - "slurmdbd is active"
+          - "{{ slurmdbd_port_check.stdout_lines }}"
+
+  handlers:
+    - name: Restart slurmdbd
+      ansible.builtin.systemd:
+        name: slurmdbd
+        state: restarted