fix: cube-sphere communitcator rank limits

[romanc]

Description

Weaken the cube-sphere communicator hard ranks limit. We need "at least" not "exactly" the rank number. Iirc this has especially been an issue with "io rank" when running integrated into GEOS.

This is part of building back the "opt_cycle_I"-branch, i.e. trying to get #465 into a smaller changeset.

How has this been tested?

Running dynamics as part of the June push. @FlorianDeconinck is there an easy way to test this?

Checklist

• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas: N/A
• I have made corresponding changes to the documentation (e.g. add new modules to docs/docstrings/): N/A
• My changes generate no new warnings
• Any dependent changes have been merged and published in downstream modules
• New check tests, if applicable, are included
  ???

[FlorianDeconinck]

Not really a good way to test this, apart from a mock MPI and a rather silly test. It is a very "operation" oriented case where you oversubscribe your nodes because you need IO to get nodes, but since we are below the infrastructure layer we can reason on the all structure

[FlorianDeconinck]

LGTM

[romanc]

Alright - in that case, let's just merge as-is saying that we've tested (extensively) with recent runs integrated in GEOS (which is the final bar anyway).