Add support for autodetection of gres resources

Author: jovial

README.md

@@ -59,9 +59,10 @@ unique set of homogenous nodes:
   `free --mebi` total * `openhpc_ram_multiplier`.
   * `ram_multiplier`: Optional.  An override for the top-level definition
   `openhpc_ram_multiplier`. Has no effect if `ram_mb` is set.
-  * `gres`: Optional. List of dicts defining [generic resources](https://slurm.schedmd.com/gres.html). Each dict must define:
+  * `gres_autodetect`: Optional. The [auto detection mechanism](https://slurm.schedmd.com/gres.conf.html#OPT_AutoDetect) to use for the  generic resources. Note: you must still define the `gres` dictionary (see below) but you only need the define the `conf` key.
+  * `gres`: Optional. List of dicts defining [generic resources](https://slurm.schedmd.com/gres.html). Each dict should define:
       - `conf`: A string with the [resource specification](https://slurm.schedmd.com/slurm.conf.html#OPT_Gres_1) but requiring the format `<name>:<type>:<number>`, e.g. `gpu:A100:2`. Note the `type` is an arbitrary string.
-      - `file`: A string with the [File](https://slurm.schedmd.com/gres.conf.html#OPT_File) (path to device(s)) for this resource, e.g. `/dev/nvidia[0-1]` for the above example.
+      - `file`: Omit if `gres_autodetect` is set. A string with the [File](https://slurm.schedmd.com/gres.conf.html#OPT_File) (path to device(s)) for this resource, e.g. `/dev/nvidia[0-1]` for the above example.
     Note [GresTypes](https://slurm.schedmd.com/slurm.conf.html#OPT_GresTypes) must be set in `openhpc_config` if this is used.
   * `features`: Optional. List of [Features](https://slurm.schedmd.com/slurm.conf.html#OPT_Features) strings.
   * `node_params`: Optional. Mapping of additional parameters and values for

templates/gres.conf.j2

@@ -1,11 +1,19 @@
 AutoDetect=off
 {% for nodegroup in openhpc_nodegroups %}
-{%      for gres in nodegroup.gres | default([]) %}
-{%          set gres_name, gres_type, _ = gres.conf.split(':') %}
-{%          set inventory_group_name = openhpc_cluster_name ~ '_' ~ nodegroup.name %}
-{%          set inventory_group_hosts = groups.get(inventory_group_name, []) %}
+{%      set gres_list = nodegroup.gres | default([]) %}
+{%      set gres_autodetect = nodegroup.gres_autodetect | default('off') %}
+{%      set inventory_group_name = openhpc_cluster_name ~ '_' ~ nodegroup.name %}
+{%      set inventory_group_hosts = groups.get(inventory_group_name, []) %}
+{%      if gres_autodetect | default('off') != 'off'  %}
 {%          for hostlist in (inventory_group_hosts | hostlist_expression) %}
-NodeName={{ hostlist }} Name={{ gres_name }} Type={{ gres_type }} File={{ gres.file }}
+NodeName={{ hostlist }} AutoDetect={{ gres_autodetect }}
 {%          endfor %}{# hostlists #}
-{%      endfor %}{# gres #}
+{%      else %}
+{%          for gres in gres_list %}
+{%              set gres_name, gres_type, _ = gres.conf.split(':') %}
+{%              for hostlist in (inventory_group_hosts | hostlist_expression) %}
+NodeName={{ hostlist }} Name={{ gres_name }} Type={{ gres_type }} File={{ gres.file | mandatory('The gres configuration dictionary: ' ~  gres ~ ' is missing the file key, but gres_autodetect is set to off. The error occured on node group: ' ~  nodegroup.name ~ '. Please add the file key or set gres_autodetect.') }}
+{%              endfor %}{# hostlists #}
+{%          endfor %}{# gres #}
+{%      endif %}{# autodetect #}
 {% endfor %}{# nodegroup #}