# esh-pve-nas cutover, step 1 of 5 — quiesce esh-docker-vm's hard NFS mounts.
#
# Run:  scripts/elway infra-ops@10.0.50.45 --playbook playbooks/esh-cutover-1-quiesce-docker-vm.yaml
#
# Why this is first and why it is not optional: /mnt/books and /mnt/backup are
# `hard` NFS from CT 103 on esh-pve-nas. A hard mount does not fail when the
# server goes away — it blocks forever in D-state, and the only known remedy is
# rebooting THIS host. /mnt/books was deliberately left hard because calibre's
# SQLite risks corruption under `soft`, so the mount option is not the fix; the
# quiesce is.
#
# Measured 2026-08-18: exactly one container binds these paths
# (calibre-web-automated -> /mnt/books/calibre/{ingest,calibre_library}) and
# /mnt/backup has no container consumers at all. The blast radius is one service,
# not the seventeen containers on this host.
#
# Reversed by playbooks/esh-cutover-5-restore.yaml.

steps:
  # No --format here: elway substitutes {{ ... }}, so Go template braces in a
  # shell command are a booby trap. --filter + -q avoids them entirely.
  - name: Stop the only container holding the NFS mounts
    shell: sudo -n docker stop calibre-web-automated
    when: "test -n \"$(sudo -n docker ps -q --filter name=^calibre-web-automated$)\""

  - name: Confirm nothing else has files open under the mounts
    shell: |
      busy=$(sudo -n lsof +D /mnt/books +D /mnt/backup 2>/dev/null | tail -n +2 | wc -l)
      if [ "$busy" -ne 0 ]; then
        echo "STILL BUSY — refusing to unmount:"
        sudo -n lsof +D /mnt/books +D /mnt/backup 2>/dev/null | head -20
        exit 1
      fi
      echo "no open files under either mount"
    changed_when: "false"

  - name: Unmount /mnt/books
    shell: sudo -n umount /mnt/books
    when: "mountpoint -q /mnt/books"

  - name: Unmount /mnt/backup
    shell: sudo -n umount /mnt/backup
    when: "mountpoint -q /mnt/backup"

verify:
  - name: Neither NFS mount remains
    shell: "! findmnt -t nfs,nfs4 -o TARGET | grep -qE '/mnt/(books|backup)'"
    changed_when: "false"

  - name: The other sixteen containers are still up
    shell: |
      n=$(sudo -n docker ps -q | wc -l)
      echo "$n containers still running"
      test "$n" -ge 10
    changed_when: "false"