For a OAR setup with different set of nodes (i.e. different homogeneous clusters) in the resources, you might want to give different priorities to nodes, so that
some nodes are used in priority compared to others.

For that purpose, you can use the scheduler_priority property of the nodes (setting it using the oarnodesetting command), which will be taken into account as specified per the
SCHEDULER_RESOURCE_ORDER configuration setting in oar.conf.


Please mind also adding a 'cluster' property (oarproperty command and
then oarnodesetting command) to identify cluster easly in oarsub
commands, if one of the concern is to not have job mix nodes from old
and new clusters.

e.g.:

<code bash>
$ oarsub -p "cluster = 'my_brand_new_cluster'" ...
</code>

which would be equivalent but maybe less cryptic than:

<code bash>
 $ oarsub -p "scheduler_priority = <value for the new cluster>'" ...
</code>

The scheduler priority being a integer, it however allows for a -p
switch such as "scheduler_priority >= <value>'", let
say if you have more than 3 clusters.