ocp-ing-ichp-materials/playbooks/roles/user-workload-monitoring/tasks/main.yml

---
# Ensures user workload monitoring is enabled.
#
# XXX: Only needed for the TODO items below.
#- name: Load the main configmap if it is there already.
#  kubernetes.core.k8s_info:
#    kubeconfig: tmp/kubeconfig-ocp4
#    validate_certs: no
#    api_version: v1
#    kind: configmap
#    namespace: openshift-monitoring
#    name: cluster-monitoring-config
#  register: cmc_is_there
#
# TODO
#- name: Extract the contents of config.yaml from cm if it existed.
#
# TODO
#- name: Merge the existing config.yaml and our additions.
#
# TODO: do the same for uwm-alertmanager
#
# TODO: might want to add alert-routing-edit rolebinding to create-ichp-project/templates/project-template.yml
#
# XXX: Exclude projects by adding "openshift.io/user-monitoring=false" label.
#       https://docs.redhat.com/en/documentation/openshift_container_platform/4.16/html/monitoring/configuring-user-workload-monitoring
#
# TODO: Wait for components to start up?
#         app.kubernetes.io/component=controller (prometheus operator)
#         app.kubernetes.io/component=prometheus (prometheus pods)
#         app.kubernetes.io/name=thanos-ruler (thanos pods)
#         alertmanager=user-workload (alertmanager pods)
#
- name: Ensure that the main configmap is defined.
  kubernetes.core.k8s:
    kubeconfig: tmp/kubeconfig-ocp4
    validate_certs: no
    api_version: v1
    kind: configmap
    namespace: openshift-monitoring
    name: cluster-monitoring-config
    resource_definition:
      data:
        config.yaml: |
          enableUserWorkload: true
          alertmanagerMain:
            enableUserAlertmanagerConfig: true
          prometheusK8s:
            retention: 1w
            retentionSize: 4Gi
            volumeClaimTemplate:
              spec:
                storageClassName: nfs-storage
                resources:
                  requests:
                    storage: 4Gi

- name: Ensure that the uwm alertmanager configmap is defined.
  kubernetes.core.k8s:
    kubeconfig: tmp/kubeconfig-ocp4
    validate_certs: no
    api_version: v1
    kind: configmap
    namespace: openshift-user-workload-monitoring
    name: user-workload-monitoring-config
    resource_definition:
      data:
        config.yaml: |
          alertmanager:
            enabled: true
            enableAlertmanagerConfig: true
          prometheus:
            retention: 1w
            retentionSize: 4Gi
            volumeClaimTemplate:
              spec:
                storageClassName: nfs-storage
                resources:
                  requests:
                    storage: 4Gi
          thanosRuler:
            retention: 1w
            volumeClaimTemplate:
              spec:
                storageClassName: nfs-storage
                resources:
                  requests:
                    storage: 4Gi
...