feat: Add RKE2 as alternative Kubernetes distribution for service cluster

Add support for deploying RKE2 (Rancher Kubernetes Engine 2) as an alternative
to vanilla Kubernetes (kubeadm) for the service cluster. Users can choose the
distribution via the new k8s_distro field in omnia_config.yml.

Configuration changes:
- Add k8s_distro field to service_k8s_cluster in omnia_config.yml (default: kubeadm)
- Update omnia_config.json schema to validate k8s_distro enum (kubeadm/rke2)
- Expand k8s_cni enum to include canal, cilium (RKE2-supported CNIs)

Pipeline integration:
- discovery.yml: Enable service_k8s tag when service_rke2 is in software_config.json
- include_software_config.yml: Detect service_rke2 and set service_rke2_support fact
- validate_software_config_json.yml: Handle service_rke2 arch and version detection
- common_validation.py: Accept service_rke2 for cluster validation
- image_package_collector.py: Dynamically select service_rke2.json for image builds
- k8s_config/main.yml: Branch NFS setup based on k8s_distro
- configure_cloud_init_group.yml: Select RKE2-specific templates when k8s_distro=rke2

New files:
- 3 RKE2 cloud-init templates (first server, additional server, agent)
- create_rke2_config_nfs.yml for RKE2-specific NFS directory setup
- service_rke2.json package definitions for RHEL 10.0 x86_64

Key differences from kubeadm path:
- RKE2 uses built-in containerd (no CRI-O)
- RKE2 manages CNI lifecycle (calico/canal/cilium/flannel)
- Token-based cluster join instead of kubeadm certificates
- kube-vip deployed as RKE2 static pod manifest
- RKE2 registries.yaml for Pulp mirror integration
- Port 9345 for RKE2 supervisor API

Existing kubeadm deployment is completely unaffected when k8s_distro=kubeadm (default).

Signed-off-by: John Lockman <j.lockman@dell.com>

Author: j0hnL

common/library/module_utils/input_validation/schema/omnia_config.json

@@ -106,8 +106,13 @@
           "deployment": {
             "type": "boolean"
           },
+          "k8s_distro": {
+            "enum": ["kubeadm", "rke2"],
+            "default": "kubeadm",
+            "description": "Kubernetes distribution to deploy. kubeadm for vanilla K8s, rke2 for RKE2."
+          },
           "k8s_cni": {
-            "enum": ["calico"],
+            "enum": ["calico", "canal", "cilium", "flannel"],
             "description": "K8s CNI plugin to use for this cluster."
           },
           "pod_external_ip_range": { 

common/library/module_utils/input_validation/validation_flows/common_validation.py

@@ -931,7 +931,7 @@ def validate_k8s(data, admin_networks, softwares, ha_config, tag_names, errors,
     # service_k8s_cluster = data["service_k8s_cluster"]
     cluster_set = {}
 
-    if "service_k8s" in softwares and "service_k8s" in tag_names:
+    if ("service_k8s" in softwares or "service_rke2" in softwares) and "service_k8s" in tag_names:
         cluster_set["service_k8s_cluster"] = data.get(
             "service_k8s_cluster", [])
 

common/library/modules/image_package_collector.py

@@ -109,11 +109,15 @@ def collect_packages_from_json(sw_data, fg_name=None,
     elif service_k8s_defined:
         fg_name = fg_name.replace("_aarch64", "").replace("_x86_64", "")
 
-        if "service_k8s" in sw_data and "cluster" in sw_data["service_k8s"]:
-            for entry in sw_data["service_k8s"]["cluster"]:
+        # Determine the top-level key (service_k8s or service_rke2)
+        k8s_top_key = "service_rke2" if "service_rke2" in sw_data else "service_k8s"
+
+        if k8s_top_key in sw_data and "cluster" in sw_data[k8s_top_key]:
+            for entry in sw_data[k8s_top_key]["cluster"]:
                 if entry.get("type") == "rpm" and "package" in entry:
                     packages.append(entry["package"])
 
+
         if fg_name in sw_data and "cluster" in sw_data[fg_name]:
             for entry in sw_data[fg_name]["cluster"]:
                 if entry.get("type") == "rpm" and "package" in entry:
@@ -170,7 +174,7 @@ def process_functional_group(fg_name, arch, os_version, input_project_dir,
                     sw_data, fg_name=fg_name, slurm_defined=True
                 )
             )
-        elif json_file == "service_k8s.json":
+        elif json_file in ("service_k8s.json", "service_rke2.json"):
             packages.extend(
                 collect_packages_from_json(
                     sw_data, fg_name=fg_name, service_k8s_defined=True
@@ -230,12 +234,15 @@ def run_module():
     allowed_additional_subgroups = get_allowed_additional_subgroups(software_config) if additional_enabled else []
 
     # pylint: disable=line-too-long
+    # Determine which K8s package JSON to use based on software_config.json
+    k8s_json = "service_rke2.json" if "service_rke2" in allowed_softwares else "service_k8s.json"
+
     # Functional group → json files mapping
     software_map = {
         "default_x86_64": ["openldap.json"],
-        "service_kube_node_x86_64": ["service_k8s.json"],
-        "service_kube_control_plane_first_x86_64": ["service_k8s.json"],
-        "service_kube_control_plane_x86_64": ["service_k8s.json"],
+        "service_kube_node_x86_64": [k8s_json],
+        "service_kube_control_plane_first_x86_64": [k8s_json],
+        "service_kube_control_plane_x86_64": [k8s_json],
         "slurm_control_node_x86_64": ["slurm_custom.json", "openldap.json", "ldms.json"],
         "slurm_node_x86_64": ["slurm_custom.json", "openldap.json", "ldms.json"],
         "login_node_x86_64": ["slurm_custom.json", "openldap.json", "ldms.json"],

discovery/discovery.yml

@@ -67,6 +67,9 @@
               (
                 ['service_k8s']
                 if ( 'service_k8s' in (
+                    lookup('file', hostvars['localhost']['input_project_dir'] ~ '/software_config.json')
+                    | from_json).softwares | map(attribute='name') | list
+                  or 'service_rke2' in (
                     lookup('file', hostvars['localhost']['input_project_dir'] ~ '/software_config.json')
                     | from_json).softwares | map(attribute='name') | list )
                 else []

discovery/roles/configure_ochami/tasks/configure_cloud_init_group.yml

@@ -25,11 +25,21 @@
   changed_when: true
   failed_when: false
 
+- name: Determine cloud-init template path based on k8s_distro # noqa: yaml[line-length]
+  ansible.builtin.set_fact:
+    ci_group_template_src: >-
+      {%- if k8s_distro | default('kubeadm') == 'rke2' and
+          'service_kube' in functional_group_name -%}
+        cloud_init/rke2/ci-group-{{ functional_group_name }}.yaml.j2
+      {%- else -%}
+        cloud_init/ci-group-{{ functional_group_name }}.yaml.j2
+      {%- endif -%}
+
 - name: Load ci group template
   block:
     - name: Load ci group template - {{ functional_group_name }}
       ansible.builtin.template:
-        src: "cloud_init/ci-group-{{ functional_group_name }}.yaml.j2"
+        src: "{{ ci_group_template_src | trim }}"
         dest: "{{ cloud_init_dir }}/ci-group-{{ functional_group_name }}.yaml"
         mode: "{{ hostvars['localhost']['file_permissions_644'] }}"
   rescue: