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 +1,16 @@
+# Managed by Ansible
+# Slurm cgroup configuration
+
+CgroupPlugin=autodetect
+
+ConstrainCores=yes
+ConstrainRAMSpace=yes
+ConstrainSwapSpace=no
+ConstrainDevices=yes
+
+AllowedRAMSpace=100
+AllowedSwapSpace=0
+MaxRAMPercent=100
+MaxSwapPercent=0
+
+MinRAMSpace=30
@@ -0,0 +1,4 @@
+# Managed by Ansible
+{% for node in slurm_nodes if node.managed_state | default('present') == 'present' and node.gres | default('') | length > 0 %}
+NodeName={{ node.name }} Name=gpu File={{ node.gres_file | default('/dev/nvidia0') }}
+{% endfor %}
@@ -0,0 +1,67 @@
+# Managed by Ansible
+
+ClusterName={{ slurm_cluster_name }}
+SlurmctldHost={{ slurm_control_machine }}({{ slurm_control_addr }})
+
+SlurmUser={{ slurm_user }}
+AuthType=auth/munge
+StateSaveLocation=/var/spool/slurmctld
+SlurmdSpoolDir=/var/spool/slurmd
+SwitchType=switch/none
+MpiDefault={{ slurm_default_mpi_type }}
+ProctrackType={{ slurm_proctrack_type }}
+ReturnToService={{ slurm_return_to_service }}
+{% if slurm_gres_types is defined and slurm_gres_types | length > 0 %}
+GresTypes={{ slurm_gres_types }}
+{% endif %}
+
+SlurmctldPidFile=/run/slurmctld.pid
+SlurmdPidFile=/run/slurmd.pid
+SlurmctldPort={{ slurmctld_port }}
+SlurmdPort={{ slurmd_port }}
+
+TaskPlugin={{ slurm_task_plugin }}
+SelectType={{ slurm_select_type }}
+SelectTypeParameters={{ slurm_select_type_parameters }}
+
+SchedulerType=sched/backfill
+# Priority / fairshare
+PriorityType={{ slurm_priority_type | default('priority/multifactor') }}
+PriorityDecayHalfLife={{ slurm_priority_decay_half_life | default('7-0') }}
+PriorityCalcPeriod={{ slurm_priority_calc_period | default(5) }}
+PriorityFavorSmall={{ slurm_priority_favor_small | default('NO') }}
+PriorityWeightAge={{ slurm_priority_weight_age | default(1000) }}
+PriorityWeightFairshare={{ slurm_priority_weight_fairshare | default(10000) }}
+PriorityWeightJobSize={{ slurm_priority_weight_job_size | default(1000) }}
+PriorityWeightPartition={{ slurm_priority_weight_partition | default(1000) }}
+PriorityWeightQOS={{ slurm_priority_weight_qos | default(10000) }}
+PriorityMaxAge={{ slurm_priority_max_age | default('1-0') }}
+
+SlurmctldTimeout=120
+SlurmdTimeout=300
+InactiveLimit=0
+KillWait=30
+Waittime=0
+
+AccountingStorageType={{ slurm_accounting_storage_type }}
+{% if slurm_accounting_storage_type == "accounting_storage/slurmdbd" %}
+AccountingStorageHost={{ slurm_accounting_storage_host }}
+AccountingStoragePort={{ slurm_accounting_storage_port }}
+AccountingStorageEnforce={{ slurm_accounting_storage_enforce | default('associations,limits,qos') }}
+AccountingStorageTRES={{ slurm_accounting_storage_tres | default('cpu,mem,energy,node,billing,fs/disk,pages,vmem,gres/gpu') }}
+{% endif %}
+JobAcctGatherType={{ slurm_job_acct_gather_type | default('jobacct_gather/none') }}
+JobCompType={{ slurm_job_comp_type }}
+
+SlurmctldDebug=info
+SlurmdDebug=info
+SlurmctldLogFile=/var/log/slurm/slurmctld.log
+SlurmdLogFile=/var/log/slurm/slurmd.log
+
+{% for node in slurm_nodes if node.managed_state | default('present') == 'present' %}
+NodeName={{ node.name }} NodeAddr={{ node.addr }} CPUs={{ node.cpus }}{% if node.topology | default('') | length > 0 %} {{ node.topology }}{% endif %} RealMemory={{ node.real_memory }}{% if node.gres | default('') | length > 0 %} Gres={{ node.gres }}{% endif %}{% if node.features | default('') | length > 0 %} Feature={{ node.features }}{% endif %} State=UNKNOWN
+{% endfor %}
+
+{% for partition in slurm_partitions %}
+PartitionName={{ partition.name }} Nodes={{ partition.nodes }} Default={{ partition.default }} MaxTime={{ partition.max_time }} State={{ partition.state }}
+{% endfor %}
@@ -0,0 +1,38 @@
+# Managed by Ansible
+# Slurm database daemon configuration
+
+AuthType=auth/munge
+
+DbdHost={{ slurmdbd_host }}
+DbdPort={{ slurmdbd_port }}
+
+SlurmUser={{ slurm_user }}
+
+DebugLevel=info
+LogFile=/var/log/slurm/slurmdbd.log
+PidFile=/run/slurmdbd.pid
+
+CommitDelay={{ slurmdbd_commit_delay | default(1) }}
+
+StorageType={{ slurmdbd_storage_type }}
+StorageHost={{ slurmdbd_storage_host }}
+StoragePort={{ slurmdbd_storage_port }}
+StorageLoc={{ slurmdbd_storage_loc }}
+StorageUser={{ slurmdbd_storage_user }}
+StoragePass={{ slurmdbd_storage_pass }}
+
+# Retention / purge policy
+PurgeEventAfter={{ slurmdbd_purge_event_after | default('12months') }}
+PurgeJobAfter={{ slurmdbd_purge_job_after | default('12months') }}
+PurgeResvAfter={{ slurmdbd_purge_resv_after | default('12months') }}
+PurgeStepAfter={{ slurmdbd_purge_step_after | default('3months') }}
+PurgeSuspendAfter={{ slurmdbd_purge_suspend_after | default('3months') }}
+PurgeTXNAfter={{ slurmdbd_purge_txn_after | default('12months') }}
+PurgeUsageAfter={{ slurmdbd_purge_usage_after | default('24months') }}
+
+ArchiveEvents={{ slurmdbd_archive_events | default('no') }}
+ArchiveJobs={{ slurmdbd_archive_jobs | default('no') }}
+ArchiveSteps={{ slurmdbd_archive_steps | default('no') }}
+ArchiveSuspend={{ slurmdbd_archive_suspend | default('no') }}
+ArchiveTXN={{ slurmdbd_archive_txn | default('no') }}
+ArchiveUsage={{ slurmdbd_archive_usage | default('no') }}