Merge pull request #12 from stackhpc/partition-maxtime

Partition maxtime

Author: brtkwr

README.md

@@ -13,7 +13,19 @@ Role Variables
 
 `openhpc_slurm_control_host`: ansible host name of the controller e.g `"{{ groups['cluster_control'] | first }}"`
 
-`openhpc_slurm_partitions`: list of slurm partitions
+`openhpc_slurm_partitions`: list of one or more slurm partitions.  Each partition may contain the following values:
+* `groups`: If there are multiple node groups that make up the partition, a list of group objects can be defined here.
+  Otherwise, `groups` can be omitted and the following attributes can be defined in the partition object.
+  * `name`: The name of the nodes within this group.
+  * `cluster_name`: Optional.  An override for the top-level definition `openhpc_cluster_name`.
+  * `num_nodes`: Nodes within the group are assumed to number `0:num_nodes-1`.
+  * `ram_mb`: Optional.  The physical RAM available in each server of this group.
+  Compute node hostnames are assumed to take the form: `cluster_name-group_name-{0..num_nodes-1}`
+* `default`: Optional.  A boolean flag for whether this partion.  Valid settings are `YES` and `NO`.
+* `maxtime`: Optional.  A partition-specific time limit in hours, minutes and seconds.  The default value is
+  `openhpc_job_maxtime`, which defaults to `24:00:00`.
+
+`openhpc_job_maxtime`: A maximum time job limit in hours, minutes and seconds.  The default is `24:00:00`.
 
 `openhpc_cluster_name`: name of the cluster
 

defaults/main.yml

@@ -8,6 +8,7 @@ openhpc_packages: []
 openhpc_drain_timeout: 86400
 openhpc_resume_timeout: 300
 openhpc_retry_delay: 10
+openhpc_job_maxtime: 24:00:00
 openhpc_enable:
   control: false
   batch: false

templates/slurm.conf.j2

@@ -121,7 +121,11 @@ NodeName={{group.cluster_name|default(openhpc_cluster_name)}}-{{group.name}}-[0-
 {% endfor %}
 {% endfor %}
 {% for part in openhpc_slurm_partitions %}
-PartitionName={{part.name}} Nodes={% for group in part.get('groups', [part]) %}{{group.cluster_name|default(openhpc_cluster_name)}}-{{group.name}}-[0-{{group.num_nodes|int-1}}]{% if not loop.last %},{% endif %}{% endfor %} Default=YES MaxTime=24:00:00 State=UP
+PartitionName={{part.name}} \
+    Nodes={% for group in part.get('groups', [part]) %}{{group.cluster_name|default(openhpc_cluster_name)}}-{{group.name}}-[0-{{group.num_nodes|int-1}}]{% if not loop.last %},{% endif %}{% endfor %} \
+    Default={% if 'default' in part %}{{ part.default }}{% else %}YES{% endif %} \
+    MaxTime={% if 'maxtime' in part %}{{ part.maxtime }}{% else %}{{ openhpc_job_maxtime }}{% endif %} \
+    State=UP
 {% endfor %}
 # Want nodes that drop out of SLURM's configuration to be automatically 
 # returned to service when they come back.