#!/usr/bin/env bash
# =============================================================================
#  60-media-relocate — move Plex's 337 GB preview cache off the SSD.
#
#  RUN THIS ONLY AFTER THE SOAK. It is deliberately not part of bootstrap.
#
#  WHY
#  Preview thumbnails accumulate at roughly 28 MB per hour of video added. On
#  the SSD that eats the ~75 GB of headroom in one to three years. On the 3 TB
#  ext4 disk — which otherwise has no job — there is room for about 85,000 more
#  content-hours, roughly seven times the current library.
#
#  THE RISK, STATED PLAINLY
#  Plex does not support relocating Media/. It exposes exactly two relocation
#  controls: the data directory ROOT, and TranscoderTempDirectory. Putting
#  Media/ on another filesystem is a bind mount Plex is unaware of.
#
#  The specific hazard is EXDEV. Plex writes temp files and rename()s them into
#  place — the orphaned Preferences.xml.tmp.<guid> files on the old Windows
#  install are that pattern leaving fingerprints. A rename() across a
#  filesystem boundary fails unless the caller catches EXDEV and falls back to
#  copy-then-delete. Whether Plex's does cannot be reasoned about from the
#  outside. It can only be tested — which is what this script does, on exactly
#  one title, reversibly.
#
#  ROLLBACK is a single command, printed at the end.
# =============================================================================
set -uo pipefail

PLEXDIR="/srv/plex"
CFG="$PLEXDIR/config/Library/Application Support/Plex Media Server"
SRC="$CFG/Media"
DEST="/srv/data/plex-media"
OVERRIDE="$PLEXDIR/docker-compose.override.yml"

say(){ printf '\n\033[1;36m=== %s\033[0m\n' "$*"; }
ok(){  printf '  \033[1;32m[ok]\033[0m %s\n' "$*"; }
bad(){ printf '  \033[1;31m[FAIL]\033[0m %s\n' "$*"; }
note(){ printf '  %s\n' "$*"; }

[ "$(id -u)" -eq 0 ] || { bad "must run as root"; exit 1; }

# ---------------------------------------------------------------------------
say "preflight"
# ---------------------------------------------------------------------------
if ! mountpoint -q /srv/data; then
  bad "/srv/data is not mounted. Convert the 3TB disk to ext4 first (runbook Phase 11)."
  exit 1
fi
ok "/srv/data mounted: $(findmnt -no SOURCE,FSTYPE /srv/data)"

[ -d "$SRC" ] || { bad "no Media directory at $SRC"; exit 1; }
SRC_FS=$(stat -c '%m' "$SRC"); DEST_FS=$(stat -c '%m' /srv/data)
SZ=$(du -sh "$SRC" 2>/dev/null | cut -f1)
note "Media/ is $SZ on $SRC_FS, moving to $DEST_FS"

AVAIL=$(df --output=avail -BG /srv/data | tail -1 | tr -dc '0-9')
NEED=$(du -sBG "$SRC" 2>/dev/null | cut -f1 | tr -dc '0-9')
if [ "${AVAIL:-0}" -lt "$((NEED + 20))" ]; then
  bad "need ~${NEED}G + headroom, /srv/data has ${AVAIL}G"
  exit 1
fi
ok "space available: ${AVAIL}G"

# ---------------------------------------------------------------------------
say "stopping Plex"
# ---------------------------------------------------------------------------
docker compose -f "$PLEXDIR/docker-compose.yml" stop plex || true
sleep 3

# ---------------------------------------------------------------------------
say "moving Media/ (this takes a while — ~337 GB)"
# ---------------------------------------------------------------------------
install -d -o 3000 -g 3000 "$DEST"
if ! rsync -a --remove-source-files --info=progress2 "$SRC"/ "$DEST"/; then
  bad "rsync failed — Media/ left in place, nothing changed structurally"
  docker compose -f "$PLEXDIR/docker-compose.yml" start plex
  exit 1
fi
find "$SRC" -type d -empty -delete 2>/dev/null
install -d -o 3000 -g 3000 "$SRC"     # empty mountpoint for the bind
chown -R 3000:3000 "$DEST"
ok "moved, $(du -sh "$DEST" | cut -f1) now on /srv/data"

# ---------------------------------------------------------------------------
say "enabling the bind mount"
# ---------------------------------------------------------------------------
# An override file rather than editing the compose: rollback is deleting it.
cat > "$OVERRIDE" <<'YAML'
# Added by 60-media-relocate.sh. Delete this file to roll back to the
# supported single-directory layout (and move Media/ back).
services:
  plex:
    volumes:
      - type: bind
        source: /srv/data/plex-media
        target: /config/Library/Application Support/Plex Media Server/Media
YAML
ok "wrote $OVERRIDE"

docker compose -f "$PLEXDIR/docker-compose.yml" up -d
sleep 10
for i in $(seq 1 40); do
  curl -fsS -m 3 http://127.0.0.1:32400/identity >/dev/null 2>&1 && break
  sleep 3
done

if docker exec plex sh -c 'mountpoint -q "/config/Library/Application Support/Plex Media Server/Media"'; then
  ok "container sees Media/ as a mountpoint"
else
  bad "bind mount not active inside the container"
  exit 1
fi

# ---------------------------------------------------------------------------
say "THE TEST — can Plex write across the boundary?"
# ---------------------------------------------------------------------------
# Take one movie, set its existing preview index aside, force regeneration,
# and see whether a new one appears on the far side of the mount. Fully
# reversible: the saved copy is restored if generation fails.
TOKEN=$(grep -o 'PlexOnlineToken="[^"]*"' "$CFG/Preferences.xml" | cut -d'"' -f2)
[ -n "$TOKEN" ] || { bad "could not read token from Preferences.xml"; exit 1; }

KEY=$(curl -fsS "http://127.0.0.1:32400/library/sections/2/all?X-Plex-Container-Size=1&X-Plex-Token=$TOKEN" \
      | grep -o 'ratingKey="[0-9]*"' | head -1 | cut -d'"' -f2)
[ -n "$KEY" ] || { bad "could not pick a title to test with"; exit 1; }
note "test title ratingKey=$KEY"

BIF=$(find "$DEST" -name 'index-sd.bif' 2>/dev/null | head -1)
if [ -n "$BIF" ]; then
  cp -a "$BIF" /tmp/bif-safety.bak
  rm -f "$BIF"
  note "removed one index-sd.bif (backed up to /tmp/bif-safety.bak)"
else
  note "no existing .bif found to displace; watching for any new write instead"
fi

BEFORE=$(find "$DEST" -name '*.bif' -newermt '-1 minute' 2>/dev/null | wc -l)
curl -fsS -X PUT "http://127.0.0.1:32400/library/metadata/$KEY/analyze?X-Plex-Token=$TOKEN" >/dev/null 2>&1
curl -fsS -X PUT "http://127.0.0.1:32400/library/sections/2/refresh?force=1&X-Plex-Token=$TOKEN" >/dev/null 2>&1
note "triggered analyze + forced refresh; waiting up to 5 minutes"

RESULT=fail
for i in $(seq 1 60); do
  sleep 5
  NOW=$(find "$DEST" -name '*.bif' -newermt '-6 minutes' 2>/dev/null | wc -l)
  if [ "$NOW" -gt "$BEFORE" ] || { [ -n "${BIF:-}" ] && [ -f "$BIF" ]; }; then
    RESULT=pass; break
  fi
done

# Cross-device errors are unambiguous in the log if they happened.
if docker logs plex 2>&1 | tail -500 | grep -qiE 'cross-device|EXDEV|Invalid cross'; then
  bad "cross-device link errors in the Plex log — the split is NOT safe here"
  RESULT=fail
fi

echo
if [ "$RESULT" = pass ]; then
  ok "Plex wrote preview data across the filesystem boundary — layout is good"
  rm -f /tmp/bif-safety.bak
  echo
  note "SSD now holds only the database and artwork; future thumbnail growth"
  note "lands on /srv/data, which has room for ~7x the current library."
else
  bad "Plex did NOT write across the boundary. Roll back:"
  echo
  note "  rm $OVERRIDE"
  note "  docker compose -f $PLEXDIR/docker-compose.yml up -d --force-recreate"
  note "  rsync -a --remove-source-files $DEST/ \"$SRC\"/"
  [ -f /tmp/bif-safety.bak ] && note "  (restore the test file from /tmp/bif-safety.bak)"
  exit 1
fi

exit 0