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 +1,128 @@
+---
+# Example lab inventory variables. Replace addresses, users and node topology for your environment.
+
+slurm_cluster_name: labcluster
+
+slurm_control_machine: slurm-ctl01
+slurm_control_addr: 10.10.10.11
+
+slurm_config_dir: /etc/slurm
+slurm_user: slurm
+slurm_operator_user: slurmuser
+
+slurmctld_port: 6817
+slurmd_port: 6818
+
+slurm_job_comp_type: jobcomp/none
+
+slurm_select_type: select/cons_tres
+slurm_select_type_parameters: CR_Core_Memory
+
+slurm_return_to_service: 2
+slurm_default_mpi_type: none
+
+slurm_gres_types: gpu
+
+slurm_nodes:
+  - name: slurm-c01
+    managed_state: present
+    addr: 10.10.10.12
+    cpus: 2
+    real_memory: 1800
+    features: ""
+    gres: ""
+    topology: ""
+  - name: slurm-c02
+    managed_state: present
+    addr: 10.10.10.13
+    cpus: 2
+    real_memory: 1800
+    features: ""
+    gres: ""
+    topology: ""
+  - name: gpu01
+    managed_state: present
+    addr: 10.10.10.14
+    cpus: 12
+    real_memory: 60000
+    features: "gpu"
+    gres: "gpu:1"
+    gres_file: /dev/nvidia0
+    topology: "Boards=1 SocketsPerBoard=1 CoresPerSocket=6 ThreadsPerCore=2"
+
+slurm_partitions:
+  - name: debug
+    managed_state: present
+    nodes: "slurm-c[01-02]"
+    default: "YES"
+    max_time: "INFINITE"
+    state: "UP"
+  - name: gpu
+    managed_state: present
+    nodes: "gpu01"
+    default: "NO"
+    max_time: "INFINITE"
+    state: "UP"
+  - name: all
+    managed_state: present
+    nodes: "slurm-c[01-02],gpu01"
+    default: "NO"
+    max_time: "INFINITE"
+    state: "UP"
+
+# Cgroup enforcement
+slurm_enable_cgroup: true
+slurm_task_plugin: task/cgroup,task/affinity
+slurm_proctrack_type: proctrack/cgroup
+slurm_job_acct_gather_type: jobacct_gather/cgroup
+
+# Slurm accounting / SlurmDBD
+slurm_accounting_storage_type: accounting_storage/slurmdbd
+slurm_accounting_storage_host: slurm-ctl01
+slurm_accounting_storage_port: 6819
+slurm_accounting_storage_enforce: associations,limits,qos
+slurm_accounting_storage_tres: cpu,mem,energy,node,billing,fs/disk,pages,vmem,gres/gpu
+
+slurmdbd_host: slurm-ctl01
+slurmdbd_port: 6819
+slurmdbd_storage_type: accounting_storage/mysql
+slurmdbd_storage_host: localhost
+slurmdbd_storage_port: 3306
+slurmdbd_storage_loc: slurm_acct_db
+slurmdbd_storage_user: slurm
+# Use Ansible Vault in real environments. See inventories/lab/group_vars/vault.example.yml
+slurmdbd_storage_pass: "{{ vault_slurmdbd_storage_pass | default('CHANGE_ME_USE_ANSIBLE_VAULT') }}"
+
+slurm_account_name: lab
+slurm_account_description: "AI/HPC Slurm lab account"
+slurm_account_organization: "labcluster"
+
+# SlurmDBD purge / retention policy for lab
+slurmdbd_commit_delay: 1
+slurmdbd_purge_event_after: 12months
+slurmdbd_purge_job_after: 12months
+slurmdbd_purge_resv_after: 12months
+slurmdbd_purge_step_after: 3months
+slurmdbd_purge_suspend_after: 3months
+slurmdbd_purge_txn_after: 12months
+slurmdbd_purge_usage_after: 24months
+
+# Archive is disabled for the lab; backup playbooks handle database dumps.
+slurmdbd_archive_events: no
+slurmdbd_archive_jobs: no
+slurmdbd_archive_steps: no
+slurmdbd_archive_suspend: no
+slurmdbd_archive_txn: no
+slurmdbd_archive_usage: no
+
+# Slurm priority / fairshare
+slurm_priority_type: priority/multifactor
+slurm_priority_decay_half_life: 7-0
+slurm_priority_calc_period: 5
+slurm_priority_favor_small: "NO"
+slurm_priority_weight_age: 1000
+slurm_priority_weight_fairshare: 10000
+slurm_priority_weight_job_size: 1000
+slurm_priority_weight_partition: 1000
+slurm_priority_weight_qos: 10000
+slurm_priority_max_age: 1-0
@@ -0,0 +1,5 @@
+---
+# Copy this file to vault.yml and encrypt it with ansible-vault.
+# ansible-vault encrypt inventories/lab/group_vars/vault.yml
+
+vault_slurmdbd_storage_pass: CHANGE_ME