Automation Orchestrator install and tweaks

playbooks/deploy_openshift.yml

@@ -33,6 +33,9 @@
 #   Play 7: sno_deploy_lvms            — Install LVM Storage for persistent volumes
 #   Play 8: sno_deploy_nfs             — Deploy in-cluster NFS provisioner (RWX StorageClass)
 #   Play 9: sno_deploy_service_accounts — Provision ServiceAccounts for app deployers
+#   Play 10: sno_deploy_alert_tuning    — Drop single-control-plane false-positive alerts
+#
+# Recurring maintenance (separate playbook, schedule in AAP): maintain_sno_etcd.yml
 #
 # AAP deployment is in a separate playbook: deploy_aap.yml
 #
@@ -46,6 +49,7 @@
 #   ansible-navigator run playbooks/deploy_openshift.yml --tags sno_deploy_lvms
 #   ansible-navigator run playbooks/deploy_openshift.yml --tags sno_deploy_nfs
 #   ansible-navigator run playbooks/deploy_openshift.yml --tags sno_deploy_service_accounts
+#   ansible-navigator run playbooks/deploy_openshift.yml --tags sno_deploy_alert_tuning
 
 # ---------------------------------------------------------------------------
 # Play 1: Create SNO VM in Proxmox
@@ -438,3 +442,20 @@
         data:
           token: "{{ __ocp_service_account_token }}"
       no_log: true
+
+# ---------------------------------------------------------------------------
+# Play 10: Drop platform alerts that are false positives on a single
+# control-plane cluster (AlertRelabelConfig in openshift-monitoring)
+# ---------------------------------------------------------------------------
+- name: Tune platform alerts for single-node OpenShift
+  hosts: sno.openshift.toal.ca
+  gather_facts: false
+  connection: local
+  tags: sno_deploy_alert_tuning
+
+  environment:
+    KUBECONFIG: "{{ ocp_kubeconfig | default('~/.kube/config') }}"
+    K8S_AUTH_VERIFY_SSL: "false"
+
+  roles:
+    - role: sno_alert_tuning

playbooks/maintain_sno_etcd.yml

@@ -0,0 +1,23 @@
+---
+# Defragment etcd on the single-node OpenShift cluster.
+#
+# OpenShift disables automatic etcd defragmentation on single-control-plane
+# clusters, so run this on a schedule (e.g. weekly AAP schedule, off-hours).
+# It only defragments when fragmentation exceeds the thresholds of the
+# etcdDatabaseHighFragmentationRatio alert; otherwise it reports and exits.
+#
+# Usage:
+#   ansible-navigator run playbooks/maintain_sno_etcd.yml --mode stdout
+#   ansible-navigator run playbooks/maintain_sno_etcd.yml --mode stdout -e sno_etcd_defrag_force=true
+
+- name: Defragment etcd on single-node OpenShift
+  hosts: sno.openshift.toal.ca
+  gather_facts: false
+  connection: local
+
+  environment:
+    KUBECONFIG: "{{ ocp_kubeconfig | default('~/.kube/config') }}"
+    K8S_AUTH_VERIFY_SSL: "false"
+
+  roles:
+    - role: sno_etcd_defrag