#!/usr/bin/env bash
# Move a single VM/CT from one Proxmox node to another via vzdump +
# qmrestore/pct restore -- the same relay pattern as
# clone-pve1-to-pve-test.sh, but for a *migration* (the guest ends up
# living on the target node only) rather than a *clone* (a disposable
# copy, source untouched, fresh MAC).
#
# There is no real `qm migrate` here: that command only works between
# nodes in the same Proxmox cluster with shared/replicated storage, which
# pve1 and pve-test are not (see CLAUDE.md's "Two Proxmox nodes" section --
# they're deliberately separate, unclustered nodes). This script is the
# closest equivalent across two independent nodes, built out of the same
# primitives as the clone script. It is NOT a true live migration -- read
# the caveat below before using it for anything where losing a few
# seconds/minutes of writes is unacceptable.
#
# Flow:
#   1. vzdump the resource on the source node (--mode snapshot by
#      default, so the source keeps running throughout the bulk copy --
#      this is the part that's "live": the guest stays reachable while
#      its disk data is captured and shipped to the target).
#   2. Stream the archive straight from the source node to the target
#      node (ssh source cat ... | ssh target cat > ...), same relay this
#      machine does in the clone script -- no separate on-disk staging
#      copy here either.
#   3. qmrestore / pct restore it on the target node under the same VMID
#      by default (--new-vmid to pick a different one). Restored WITHOUT
#      --unique (i.e. original MAC preserved) unless --unique is passed
#      explicitly -- unlike the clone script, the source is being retired,
#      not left running alongside a copy, so there's no address collision
#      to avoid. qmrestore/pct restore don't start the guest, so nothing
#      is live on the target node yet.
#   4. Cutover: stop the guest on the source node, then (unless --no-start)
#      start it on the target node. This is the only real downtime window
#      -- everything before this point runs with the source guest still
#      up.
#   5. Unless --remove-source is passed, the now-stopped guest is LEFT ON
#      the source node as a safety net (config + disk intact, just
#      powered off) -- easy to start back up if the target copy turns out
#      to be broken. Pass --remove-source to actually destroy it there
#      once you've verified the target is good; this step gets its own
#      typed confirmation since qm destroy/pct destroy is irreversible.
#   6. Delete the vzdump archive from both nodes' storage (unless
#      --keep-backup), same as the clone script -- neither node
#      accumulates ad hoc backup files from this script.
#
# --- IMPORTANT CAVEAT: this is not byte-perfect live migration ---
# vzdump is not incremental. With the default --mode snapshot, the source
# guest keeps running (and can keep writing to disk) for the entire time
# between when the snapshot is taken and when this script stops it at
# cutover. Any writes in that window are NOT captured in the archive and
# will NOT exist on the target. For a large disk this window can be
# minutes. If the workload can't tolerate that:
#   - use --mode stop (or --mode suspend) instead, which makes the source
#     guest go down *before* vzdump reads its disk, so the archive is
#     exactly the state being migrated and cutover has nothing left to
#     lose -- at the cost of the guest being down for the whole backup
#     duration instead of just the final cutover.
#   - or don't use this script -- put both nodes in an actual Proxmox
#     cluster with shared storage and use `qm migrate --online` instead,
#     which is the real thing this script is only approximating.
#
# This script's own defaults are pve1 -> pve-test, matching
# clone-pve1-to-pve-test.sh and CLAUDE.md's "Two Proxmox nodes" section --
# but unlike that script, this one is a generic node-to-node mover: pass
# --source-node/--target-node for any other pair. Regardless of node
# names, the source resource is only ever touched here after typing the
# source VMID back to confirm, and destroying it on the source node
# (--remove-source) requires a second, separate typed confirmation.
#
# See --help for the full option list.
set -euo pipefail

repo_root="$(cd "$(dirname "$0")/../.." && pwd)"
# shellcheck source=../env.sh
source "${repo_root}/scripts/env.sh"
# shellcheck source=../lib/confirm.sh
source "${repo_root}/scripts/lib/confirm.sh"

usage() {
  cat <<EOF
Usage: $0 --vmid <n> [options]

  --vmid <n>              Required: VMID on the source node to migrate.
                           Kind (qemu VM vs LXC CT) is auto-detected.
  --new-vmid <n>           VMID to restore as on the target node
                           (default: same as --vmid).
  --mode snapshot|suspend|stop
                           vzdump backup mode (default: snapshot -- the
                           source resource keeps running until cutover;
                           requires snapshot-capable storage, e.g.
                           ZFS/LVM-thin/Ceph/qcow2). Use "stop" for a
                           byte-perfect migration with no post-snapshot
                           write gap (source goes down for the whole
                           backup duration instead of just cutover) --
                           see the caveat at the top of this script.
  --source-node <host>      (default: \$PVE1_HOST, ${PVE1_HOST})
  --target-node <host>       (default: \$PVE_TEST_HOST, ${PVE_TEST_HOST})
  --source-storage <pool>      Where vzdump writes the backup on the
                               source node (default: local).
  --target-storage <pool>       Where the restored disk/rootfs lands on
                               the target node (default: \$PROXMOX_STORAGE, ${PROXMOX_STORAGE}).
  --unique                        Restore with a fresh MAC address
                                  (--unique 1), as the clone script always
                                  does. Off by default here since the
                                  source is being retired, not left
                                  running alongside the target.
  --no-start                        Don't start the guest on the target
                                    node after cutover (default: start
                                    it).
  --remove-source                    Destroy the guest on the source
                                     node (qm destroy/pct destroy) after
                                     a successful cutover, instead of
                                     just leaving it stopped there.
                                     Irreversible -- prompts for its own
                                     typed confirmation unless --yes.
  --keep-backup                  Don't delete the vzdump archive from
                                 either node afterward (debugging aid).
  --yes                            Skip all typed confirmations (initial
                                   backup, cutover, and --remove-source
                                   if passed).
  --dry-run                          Print the full plan and skip every
                                     mutating step (vzdump, transfer,
                                     restore, cutover, destroy, delete)
                                     and every confirm prompt. Still makes
                                     read-only SSH calls to look up the
                                     source kind and check the target
                                     VMID is free -- harmless on either
                                     node.
  -h, --help
EOF
}

vmid=""
new_vmid=""
mode="snapshot"
source_node="$PVE1_HOST"
target_node="$PVE_TEST_HOST"
source_storage="local"
target_storage="$PROXMOX_STORAGE"
unique=0
start_target=1
remove_source=0
keep_backup=0
skip_confirm=0
dry_run=0

while [[ $# -gt 0 ]]; do
  case "$1" in
  --vmid) vmid="$2"; shift 2 ;;
  --new-vmid) new_vmid="$2"; shift 2 ;;
  --mode) mode="$2"; shift 2 ;;
  --source-node) source_node="$2"; shift 2 ;;
  --target-node) target_node="$2"; shift 2 ;;
  --source-storage) source_storage="$2"; shift 2 ;;
  --target-storage) target_storage="$2"; shift 2 ;;
  --unique) unique=1; shift ;;
  --no-start) start_target=0; shift ;;
  --remove-source) remove_source=1; shift ;;
  --keep-backup) keep_backup=1; shift ;;
  --yes) skip_confirm=1; shift ;;
  --dry-run) dry_run=1; shift ;;
  -h | --help) usage; exit 0 ;;
  *) echo "Unknown option: $1" >&2; usage >&2; exit 1 ;;
  esac
done

if [[ -z "$vmid" ]]; then
  echo "ERROR: --vmid is required." >&2
  usage >&2
  exit 1
fi
if [[ "$mode" != "snapshot" && "$mode" != "suspend" && "$mode" != "stop" ]]; then
  echo "ERROR: --mode must be snapshot, suspend, or stop." >&2
  exit 1
fi
[[ -z "$new_vmid" ]] && new_vmid="$vmid"

source_target="${PROXMOX_SSH_USER}@${source_node}"
target_target="${PROXMOX_SSH_USER}@${target_node}"

# No dry-run wrapper needed for the calls below: every mutating step
# (vzdump, transfer, restore, cutover, destroy, delete) is reached only
# after the --dry-run early-exit further down, so a plain `ssh` call is
# never in the dry-run path.

# --- identify the resource kind on the source node -----------------------
echo "==> Looking up VMID ${vmid} on ${source_node}..."
kind=""
if ssh "$source_target" "qm status ${vmid}" >/dev/null 2>&1; then
  kind="vm"
elif ssh "$source_target" "pct status ${vmid}" >/dev/null 2>&1; then
  kind="lxc"
else
  echo "ERROR: VMID ${vmid} doesn't exist on ${source_node} as either a VM or CT." >&2
  exit 1
fi
echo "VMID ${vmid} on ${source_node} is a ${kind}."

# --- refuse to clobber an existing resource on the target node -----------
if ssh "$target_target" "qm status ${new_vmid}" >/dev/null 2>&1 \
  || ssh "$target_target" "pct status ${new_vmid}" >/dev/null 2>&1; then
  echo "ERROR: VMID ${new_vmid} already exists on ${target_node}. Pass --new-vmid" >&2
  echo "with a free ID, or remove the existing resource there first." >&2
  exit 1
fi

echo
echo "Plan:"
echo "  source: ${kind} VMID ${vmid} on ${source_node} (storage: ${source_storage}, mode: ${mode})"
echo "  target: VMID ${new_vmid} on ${target_node} (storage: ${target_storage}," \
  "$([[ "$unique" -eq 1 ]] && echo "fresh MAC via --unique" || echo "original MAC preserved"))"
echo "  cutover: stop VMID ${vmid} on ${source_node}," \
  "$([[ "$start_target" -eq 1 ]] && echo "then start VMID ${new_vmid} on ${target_node}" || echo "target left stopped (--no-start)")"
if [[ "$remove_source" -eq 1 ]]; then
  echo "  after cutover: DESTROY VMID ${vmid} on ${source_node} (--remove-source, irreversible)"
else
  echo "  after cutover: source VMID ${vmid} left stopped (but intact) on ${source_node}"
fi
[[ "$keep_backup" -eq 1 ]] && echo "  backup archives are kept on both nodes afterward (--keep-backup)"

if [[ "$dry_run" -eq 1 ]]; then
  echo
  echo "[dry-run] No backup, transfer, restore, cutover, destroy, or delete was performed."
  exit 0
fi

if [[ "$skip_confirm" -ne 1 ]]; then
  echo
  if ! confirm_typed "$vmid" "Type the source VMID (${vmid}) to confirm backing it up from ${source_node} for migration: "; then
    echo "Cancelled -- input didn't match ${vmid}." >&2
    exit 1
  fi
fi

# --- vzdump on the source node --------------------------------------------
echo
echo "==> Backing up VMID ${vmid} on ${source_node} (mode=${mode}, storage=${source_storage})..."
vzdump_log="$(ssh "$source_target" \
  "vzdump ${vmid} --mode ${mode} --storage ${source_storage} --compress zstd" 2>&1)" \
  || {
    echo "$vzdump_log" >&2
    echo "ERROR: vzdump failed on ${source_node}." >&2
    exit 1
  }
echo "$vzdump_log"

archive="$(echo "$vzdump_log" | grep -oP "creating vzdump archive '\K[^']+" | tail -n1)"
if [[ -z "$archive" ]]; then
  echo "ERROR: couldn't find the archive path in vzdump's output above." >&2
  exit 1
fi
archive_basename="$(basename "$archive")"
target_tmp_archive="/var/tmp/${archive_basename}"
echo "Archive: ${archive}"

# Always clean up the relayed copy on the target node, success or failure
# -- it's only ever a working copy, restored or not.
cleanup_target_tmp() {
  if [[ "$keep_backup" -ne 1 ]]; then
    ssh "$target_target" "rm -f '${target_tmp_archive}'" >/dev/null 2>&1 || true
  fi
}
trap cleanup_target_tmp EXIT

# --- relay the archive from source to target ------------------------------
echo
echo "==> Transferring archive to ${target_node}..."
ssh "$source_target" "cat '${archive}'" | ssh "$target_target" "cat > '${target_tmp_archive}'"

# --- restore on the target node --------------------------------------------
echo
echo "==> Restoring as VMID ${new_vmid} on ${target_node} (storage=${target_storage})..."
restore_unique_flag=0
[[ "$unique" -eq 1 ]] && restore_unique_flag=1
if [[ "$kind" == "vm" ]]; then
  ssh "$target_target" "qmrestore '${target_tmp_archive}' ${new_vmid} --storage ${target_storage} --unique ${restore_unique_flag}"
else
  ssh "$target_target" "pct restore ${new_vmid} '${target_tmp_archive}' --storage ${target_storage} --unique ${restore_unique_flag}"
fi
echo "Restored on ${target_node}. Source VMID ${vmid} on ${source_node} is still up --" \
  "the guest hasn't moved yet."

# --- cutover: stop source, start target -----------------------------------
if [[ "$skip_confirm" -ne 1 ]]; then
  echo
  if ! confirm_typed "$vmid" "Type the source VMID (${vmid}) again to confirm CUTOVER (stop it on ${source_node}$([[ "$start_target" -eq 1 ]] && echo ", start VMID ${new_vmid} on ${target_node}")): "; then
    echo "Cancelled before cutover -- input didn't match ${vmid}." >&2
    echo "The restored (but not started) copy remains on ${target_node} as VMID ${new_vmid};" >&2
    echo "the source on ${source_node} is untouched. Re-run cutover manually, or clean up" >&2
    echo "the target copy if you no longer want it." >&2
    exit 1
  fi
fi

echo
echo "==> Stopping VMID ${vmid} on ${source_node}..."
if [[ "$kind" == "vm" ]]; then
  ssh "$source_target" "qm stop ${vmid}"
else
  ssh "$source_target" "pct stop ${vmid}"
fi

if [[ "$start_target" -eq 1 ]]; then
  echo
  echo "==> Starting VMID ${new_vmid} on ${target_node}..."
  if [[ "$kind" == "vm" ]]; then
    ssh "$target_target" "qm start ${new_vmid}"
  else
    ssh "$target_target" "pct start ${new_vmid}"
  fi
fi

# --- optionally destroy the now-stopped source resource -------------------
if [[ "$remove_source" -eq 1 ]]; then
  if [[ "$skip_confirm" -ne 1 ]]; then
    echo
    if ! confirm_typed "$vmid" "Type the source VMID (${vmid}) one more time to permanently DESTROY it on ${source_node}: "; then
      echo "Cancelled -- input didn't match ${vmid}." >&2
      echo "VMID ${vmid} on ${source_node} is left stopped (not destroyed). VMID ${new_vmid}" >&2
      echo "on ${target_node} is up and running." >&2
      exit 1
    fi
  fi
  echo
  echo "==> Destroying VMID ${vmid} on ${source_node}..."
  if [[ "$kind" == "vm" ]]; then
    ssh "$source_target" "qm destroy ${vmid} --purge"
  else
    ssh "$source_target" "pct destroy ${vmid} --purge"
  fi
fi

# --- clean up backup archives now that the migration succeeded -----------
if [[ "$keep_backup" -ne 1 ]]; then
  echo
  echo "==> Deleting backup archive from ${source_node}'s ${source_storage} storage..."
  ssh "$source_target" "rm -f '${archive}' '${archive}.notes' '${archive}.log'" >/dev/null 2>&1 || true
fi

echo
echo "Done. VMID ${new_vmid} (${kind}) is now on ${target_node}, migrated from" \
  "VMID ${vmid} on ${source_node}."
if [[ "$remove_source" -ne 1 ]]; then
  echo "The source copy is stopped but still present on ${source_node} -- re-run with" \
    "--remove-source once you've verified the target, or remove it manually."
fi