feat(cluster_healthcheck): add cluster health validation role

playbooks/cluster_healthcheck.yml

@@ -0,0 +1,10 @@
+---
+- name: Run cluster healthchecks
+  hosts: localhost
+  connection: local
+  gather_facts: false
+  tasks:
+    - name: Include cluster_healthcheck role
+      ansible.builtin.import_role:
+        name: infra.openshift_virtualization_migration.cluster_healthcheck
+...

roles/cluster_healthcheck/README.md

@@ -0,0 +1,69 @@
+# cluster_healthcheck
+
+```
+Role belongs to infra/openshift_virtualization_migration
+Namespace - infra
+Collection - openshift_virtualization_migration
+```
+
+Description: Cluster health validation for OpenShift Virtualization migration environments.
+
+## Requirements
+
+- OpenShift cluster with `kubeconfig` configured
+- `kubernetes.core` collection installed
+- OpenShift Virtualization (CNV) operator installed
+- Migration Toolkit for Virtualization (MTV) operator installed
+
+## Role Variables
+
+### Defaults
+
+| Variable | Type | Default | Description |
+|----------|------|---------|-------------|
+| `cluster_healthcheck_checks` | list | See defaults/main.yml | List of health checks to run |
+| `cluster_healthcheck_post_migration_vms` | list | `[]` | VMs to check post-migration |
+| `cluster_healthcheck_generate_report` | bool | `true` | Generate HTML report |
+| `cluster_healthcheck_report_path` | str | `/tmp/cluster_healthcheck_report.html` | Report output path |
+| `cluster_healthcheck_mtv_namespace` | str | `openshift-mtv` | MTV operator namespace |
+| `cluster_healthcheck_kubevirt_namespace` | str | `openshift-cnv` | KubeVirt operator namespace |
+| `cluster_healthcheck_ssh_timeout` | int | `10` | SSH check timeout in seconds |
+| `cluster_healthcheck_debug` | bool | `false` | Enable verbose debug output |
+
+### Post-Migration VM Format
+
+```yaml
+cluster_healthcheck_post_migration_vms:
+  - name: my-vm
+    namespace: my-namespace
+    check_ssh: true  # optional, default false
+```
+
+## Health Checks
+
+| Check | Description |
+|-------|-------------|
+| `ocp_node_health` | Node Ready status, resource pressure, kubevirt.io/schedulable label |
+| `kubevirt_health` | HyperConverged CR, virt-* pods, CDI operator |
+| `mtv_health` | ForkliftController, MTV pods, Providers, Plans |
+| `storage_health` | StorageClasses, CSI drivers, PV capacity, pending PVCs |
+| `network_health` | Multus, NADs, OVN/SDN health, migration network |
+
+## Example Playbook
+
+```yaml
+- name: Run cluster healthchecks
+  hosts: localhost
+  connection: local
+  gather_facts: false
+  roles:
+    - role: infra.openshift_virtualization_migration.cluster_healthcheck
+      vars:
+        cluster_healthcheck_post_migration_vms:
+          - name: rhel9-vm
+            namespace: migration-target
+```
+
+## License
+
+GPL-3.0-only

roles/cluster_healthcheck/defaults/main.yml

@@ -0,0 +1,23 @@
+---
+# defaults file for cluster_healthcheck
+cluster_healthcheck_checks:
+  - ocp_node_health
+  - kubevirt_health
+  - mtv_health
+  - storage_health
+  - network_health
+
+cluster_healthcheck_post_migration_vms: []
+
+cluster_healthcheck_generate_report: true
+
+cluster_healthcheck_report_path: "/tmp/cluster_healthcheck_report.html"
+
+cluster_healthcheck_mtv_namespace: "openshift-mtv"
+
+cluster_healthcheck_kubevirt_namespace: "openshift-cnv"
+
+cluster_healthcheck_ssh_timeout: 10
+
+cluster_healthcheck_debug: false
+...

roles/cluster_healthcheck/meta/main.yml

@@ -0,0 +1,10 @@
+---
+galaxy_info:
+  author: ""
+  description: Cluster health validation for OpenShift Virtualization migration environments.
+  company: Red Hat
+  license: GPL-3.0-only
+  min_ansible_version: 2.15.0
+  galaxy_tags: []
+dependencies: []
+...

roles/cluster_healthcheck/tasks/kubevirt_health.yml

@@ -0,0 +1,177 @@
+---
+- name: kubevirt_health | Get HyperConverged CR status
+  kubernetes.core.k8s_info:
+    api_version: hco.kubevirt.io/v1beta1
+    kind: HyperConverged
+    namespace: "{{ cluster_healthcheck_kubevirt_namespace }}"
+  register: __cluster_healthcheck_hco
+
+- name: kubevirt_health | Evaluate HyperConverged conditions
+  ansible.builtin.set_fact:
+    __cluster_healthcheck_hco_available: >-
+      {{ __cluster_healthcheck_hco.resources | length > 0 and
+         __cluster_healthcheck_hco.resources[0].status.conditions | default([])
+         | selectattr('type', 'equalto', 'Available')
+         | map(attribute='status')
+         | first | default('False') == 'True' }}
+    __cluster_healthcheck_hco_degraded: >-
+      {{ __cluster_healthcheck_hco.resources | length > 0 and
+         __cluster_healthcheck_hco.resources[0].status.conditions | default([])
+         | selectattr('type', 'equalto', 'Degraded')
+         | map(attribute='status')
+         | first | default('False') == 'True' }}
+
+- name: kubevirt_health | Report HyperConverged status
+  ansible.builtin.debug:
+    msg: >-
+      HyperConverged CR -
+      Available: {{ __cluster_healthcheck_hco_available }},
+      Degraded: {{ __cluster_healthcheck_hco_degraded }}
+
+- name: kubevirt_health | Check virt-operator pods
+  kubernetes.core.k8s_info:
+    api_version: v1
+    kind: Pod
+    namespace: "{{ cluster_healthcheck_kubevirt_namespace }}"
+    label_selectors:
+      - "kubevirt.io=virt-operator"
+  register: __cluster_healthcheck_virt_operator_pods
+
+- name: kubevirt_health | Check virt-controller pods
+  kubernetes.core.k8s_info:
+    api_version: v1
+    kind: Pod
+    namespace: "{{ cluster_healthcheck_kubevirt_namespace }}"
+    label_selectors:
+      - "kubevirt.io=virt-controller"
+  register: __cluster_healthcheck_virt_controller_pods
+
+- name: kubevirt_health | Check virt-handler pods
+  kubernetes.core.k8s_info:
+    api_version: v1
+    kind: Pod
+    namespace: "{{ cluster_healthcheck_kubevirt_namespace }}"
+    label_selectors:
+      - "kubevirt.io=virt-handler"
+  register: __cluster_healthcheck_virt_handler_pods
+
+- name: kubevirt_health | Check virt-api pods
+  kubernetes.core.k8s_info:
+    api_version: v1
+    kind: Pod
+    namespace: "{{ cluster_healthcheck_kubevirt_namespace }}"
+    label_selectors:
+      - "kubevirt.io=virt-api"
+  register: __cluster_healthcheck_virt_api_pods
+
+- name: kubevirt_health | Evaluate KubeVirt pod health
+  ansible.builtin.set_fact:
+    __cluster_healthcheck_kubevirt_pods:
+      virt_operator:
+        running: "{{ __cluster_healthcheck_virt_operator_pods.resources
+                     | selectattr('status.phase', 'equalto', 'Running') | list | length }}"
+        total: "{{ __cluster_healthcheck_virt_operator_pods.resources | length }}"
+      virt_controller:
+        running: "{{ __cluster_healthcheck_virt_controller_pods.resources
+                     | selectattr('status.phase', 'equalto', 'Running') | list | length }}"
+        total: "{{ __cluster_healthcheck_virt_controller_pods.resources | length }}"
+      virt_handler:
+        running: "{{ __cluster_healthcheck_virt_handler_pods.resources
+                     | selectattr('status.phase', 'equalto', 'Running') | list | length }}"
+        total: "{{ __cluster_healthcheck_virt_handler_pods.resources | length }}"
+      virt_api:
+        running: "{{ __cluster_healthcheck_virt_api_pods.resources
+                     | selectattr('status.phase', 'equalto', 'Running') | list | length }}"
+        total: "{{ __cluster_healthcheck_virt_api_pods.resources | length }}"
+
+- name: kubevirt_health | Check CDI operator pods
+  kubernetes.core.k8s_info:
+    api_version: v1
+    kind: Pod
+    namespace: "{{ cluster_healthcheck_kubevirt_namespace }}"
+    label_selectors:
+      - "app.kubernetes.io/component=cdi-operator"
+  register: __cluster_healthcheck_cdi_operator_pods
+
+- name: kubevirt_health | Check CDI deployment pods
+  kubernetes.core.k8s_info:
+    api_version: v1
+    kind: Pod
+    namespace: "{{ cluster_healthcheck_kubevirt_namespace }}"
+    label_selectors:
+      - "app.kubernetes.io/component=cdi-deployment"
+  register: __cluster_healthcheck_cdi_deployment_pods
+
+- name: kubevirt_health | Evaluate CDI health
+  ansible.builtin.set_fact:
+    __cluster_healthcheck_cdi_pods:
+      cdi_operator:
+        running: "{{ __cluster_healthcheck_cdi_operator_pods.resources
+                     | selectattr('status.phase', 'equalto', 'Running') | list | length }}"
+        total: "{{ __cluster_healthcheck_cdi_operator_pods.resources | length }}"
+      cdi_deployment:
+        running: "{{ __cluster_healthcheck_cdi_deployment_pods.resources
+                     | selectattr('status.phase', 'equalto', 'Running') | list | length }}"
+        total: "{{ __cluster_healthcheck_cdi_deployment_pods.resources | length }}"
+
+- name: kubevirt_health | Set kubevirt health result
+  ansible.builtin.set_fact:
+    __cluster_healthcheck_results: >-
+      {{ __cluster_healthcheck_results | combine({
+           'kubevirt_health': {
+             'status': ('fail' if (not __cluster_healthcheck_hco_available or
+                                   __cluster_healthcheck_hco_degraded or
+                                   __cluster_healthcheck_kubevirt_pods.virt_operator.total | int == 0 or
+                                   __cluster_healthcheck_kubevirt_pods.virt_controller.total | int == 0)
+                        else 'pass'),
+             'details': [
+               { 'check': 'HyperConverged Available',
+                 'status': ('pass' if __cluster_healthcheck_hco_available else 'fail'),
+                 'message': ('HyperConverged CR is Available'
+                             if __cluster_healthcheck_hco_available
+                             else 'HyperConverged CR is NOT Available') },
+               { 'check': 'HyperConverged Not Degraded',
+                 'status': ('fail' if __cluster_healthcheck_hco_degraded else 'pass'),
+                 'message': ('HyperConverged CR is Degraded'
+                             if __cluster_healthcheck_hco_degraded
+                             else 'HyperConverged CR is not Degraded') },
+               { 'check': 'virt-operator',
+                 'status': ('pass' if __cluster_healthcheck_kubevirt_pods.virt_operator.running | int > 0
+                            else 'fail'),
+                 'message': (__cluster_healthcheck_kubevirt_pods.virt_operator.running | string +
+                             '/' + __cluster_healthcheck_kubevirt_pods.virt_operator.total | string +
+                             ' pods Running') },
+               { 'check': 'virt-controller',
+                 'status': ('pass' if __cluster_healthcheck_kubevirt_pods.virt_controller.running | int > 0
+                            else 'fail'),
+                 'message': (__cluster_healthcheck_kubevirt_pods.virt_controller.running | string +
+                             '/' + __cluster_healthcheck_kubevirt_pods.virt_controller.total | string +
+                             ' pods Running') },
+               { 'check': 'virt-handler',
+                 'status': ('pass' if __cluster_healthcheck_kubevirt_pods.virt_handler.running | int > 0
+                            else 'fail'),
+                 'message': (__cluster_healthcheck_kubevirt_pods.virt_handler.running | string +
+                             '/' + __cluster_healthcheck_kubevirt_pods.virt_handler.total | string +
+                             ' pods Running') },
+               { 'check': 'virt-api',
+                 'status': ('pass' if __cluster_healthcheck_kubevirt_pods.virt_api.running | int > 0
+                            else 'fail'),
+                 'message': (__cluster_healthcheck_kubevirt_pods.virt_api.running | string +
+                             '/' + __cluster_healthcheck_kubevirt_pods.virt_api.total | string +
+                             ' pods Running') },
+               { 'check': 'CDI Operator',
+                 'status': ('pass' if __cluster_healthcheck_cdi_pods.cdi_operator.running | int > 0
+                            else 'fail'),
+                 'message': (__cluster_healthcheck_cdi_pods.cdi_operator.running | string +
+                             '/' + __cluster_healthcheck_cdi_pods.cdi_operator.total | string +
+                             ' pods Running') },
+               { 'check': 'CDI Deployment',
+                 'status': ('pass' if __cluster_healthcheck_cdi_pods.cdi_deployment.running | int > 0
+                            else 'fail'),
+                 'message': (__cluster_healthcheck_cdi_pods.cdi_deployment.running | string +
+                             '/' + __cluster_healthcheck_cdi_pods.cdi_deployment.total | string +
+                             ' pods Running') }
+             ]
+           }
+         }) }}
+...

roles/cluster_healthcheck/tasks/main.yml

@@ -0,0 +1,40 @@
+---
+# tasks file for cluster_healthcheck
+- name: Initialize healthcheck results
+  ansible.builtin.set_fact:
+    __cluster_healthcheck_results:
+      ocp_node_health: { status: "skipped", details: [] }
+      kubevirt_health: { status: "skipped", details: [] }
+      mtv_health: { status: "skipped", details: [] }
+      storage_health: { status: "skipped", details: [] }
+      network_health: { status: "skipped", details: [] }
+      post_migration_vm: { status: "skipped", details: [] }
+
+- name: Include ocp_node_health tasks
+  ansible.builtin.include_tasks: ocp_node_health.yml
+  when: "'ocp_node_health' in cluster_healthcheck_checks"
+
+- name: Include kubevirt_health tasks
+  ansible.builtin.include_tasks: kubevirt_health.yml
+  when: "'kubevirt_health' in cluster_healthcheck_checks"
+
+- name: Include mtv_health tasks
+  ansible.builtin.include_tasks: mtv_health.yml
+  when: "'mtv_health' in cluster_healthcheck_checks"
+
+- name: Include storage_health tasks
+  ansible.builtin.include_tasks: storage_health.yml
+  when: "'storage_health' in cluster_healthcheck_checks"
+
+- name: Include network_health tasks
+  ansible.builtin.include_tasks: network_health.yml
+  when: "'network_health' in cluster_healthcheck_checks"
+
+- name: Include post_migration_vm tasks
+  ansible.builtin.include_tasks: post_migration_vm.yml
+  when: "cluster_healthcheck_post_migration_vms | length > 0"
+
+- name: Include report tasks
+  ansible.builtin.include_tasks: report.yml
+  when: cluster_healthcheck_generate_report
+...