---
# Deploy Ceph Tentacle cluster (cluster chosen via CEPH_ENV)
#
# Prerequisites:
#   1. All nodes provisioned and running Debian 12 with bond0 networking
#   2. SSH access via inventory.ini credentials (rendered by tofu apply)
#   3. Storage partitioned with Ceph block.db LVs and SSD OSD partitions
#
# Usage:
#   scripts/ansible-play.sh deploy-ceph.yml
#
# To run a specific phase only:
#   scripts/ansible-play.sh deploy-ceph.yml --tags bootstrap
#   scripts/ansible-play.sh deploy-ceph.yml --tags osds

- name: Deploy Ceph Tentacle cluster
  hosts: ceph_nodes
  become: true
  gather_facts: true

  pre_tasks:
    # Fail fast if the inventory was not rendered from TF. The ceph_deploy role
    # gates every phase on the ceph_bootstrap/ceph_mon/ceph_join groups and indexes
    # groups['ceph_bootstrap'][0]; against a hand-written stopgap inventory that
    # lacks them the role would error mid-run or, worse, fall through to placing a
    # MON on every host. render-inventories.sh emits these groups from TF state
    # (bootstrap = exactly one host, mon = an odd quorum including the bootstrap
    # node) - refuse to deploy against anything else.
    - name: Assert the TF-rendered placement groups are present and sane  # noqa: run-once[task]
      ansible.builtin.assert:
        that:
          - (groups['ceph_bootstrap'] | default([])) | length == 1
          - (groups['ceph_mon'] | default([])) | length >= 1
          - (groups['ceph_mon'] | default([]) | length) is odd
          - ((groups['ceph_bootstrap'] | default([])) | intersect(groups['ceph_mon'] | default([])) | length) == 1
        fail_msg: >-
          Inventory is missing or has bad TF-rendered placement groups
          (need ceph_bootstrap = exactly 1 host that is also in ceph_mon, and
          ceph_mon = a non-empty ODD quorum). Render it first:
          scripts/render-inventories.sh <partition> <region>. Refusing to deploy.
        success_msg: >-
          Placement OK: bootstrap={{ groups['ceph_bootstrap'] | default([]) | length }},
          mon={{ groups['ceph_mon'] | default([]) | length }},
          join={{ groups['ceph_join'] | default([]) | length }}.
      run_once: true

    # Per host: the address the mon/OSD/RGW bind (ceph_service_ip) must be live on
    # a local interface before bootstrap. For spice this is the fabric IP on
    # bond0.120; a node whose VLAN sub-interface did not come back after a reboot
    # would otherwise fail deep inside cephadm bootstrap/join. gather_facts is on,
    # so ansible_all_ipv4_addresses is populated.
    - name: Assert the Ceph service IP is live on this node (fabric/bond up)
      ansible.builtin.assert:
        that:
          - ceph_service_ip in ansible_all_ipv4_addresses
        fail_msg: >-
          ceph_service_ip {{ ceph_service_ip }} is not on any local interface on
          {{ inventory_hostname }} - the Ceph bind network (spice: bond0.120) is
          down on this node. Bring the fabric up before deploying it.
        success_msg: "Ceph service IP {{ ceph_service_ip }} is live on {{ inventory_hostname }}."

  roles:
    - ceph_deploy