#!/bin/bash
# ==============================================================================================
# ================================= Mover Stop =================================================
# ==============================================================================================
#
# PURPOSE
# ─────────────────────────────────────────────────────────────────────────────
# Safely stops the unRAID mover with a wall warning, configurable timeout, and
# SIGTERM → SIGKILL sequence. Use before planned reboots, disk operations, or
# any operation where mover and rsync running simultaneously could corrupt files.
# Exits cleanly if mover is not running.
#
# ==============================================================================================
# OPERATIONAL MODEL
# ==============================================================================================
#
# Stop Sequence
#   1. Check if mover is running — exit cleanly if not
#   2. Wall message to all logged-in terminal users
#   3. Wait MOVER_STOP_TIMEOUT seconds
#   4. SIGTERM — allows mover to finish its current file before stopping
#      (no partial files — the mover completes what it is working on)
#   5. Wait 5 seconds → verify stopped
#   6. SIGKILL if still running — forced stop, partial files possible
#   7. Final verify — error if still running after SIGKILL
#
# SIGTERM first because the mover has an opportunity to finish the file it is
# currently moving, leaving no partial copies on cache or array. SIGKILL is only
# used as a last resort and may leave a file split across cache and array.
#
# ==============================================================================================
# OPERATIONAL SAFEGUARDS
# ==============================================================================================
#
# Single Instance Lock
#   acquire_lock prevents concurrent stop attempts racing each other.
#
# Root Required
#   pkill on emhttp processes requires root.
#
# Final Verify
#   Confirms mover is actually stopped after the kill sequence — errors if it
#   is still running after SIGKILL.
#
# Silent When Clean
#   Mover not running = log() only, no visible output.
#
# ==============================================================================================
# CONFIGURATION
# ==============================================================================================
#
# master.conf
#
#   MOVER_STOP_TIMEOUT
#       Seconds between wall warning and SIGTERM. (default: 30)
#
# ==============================================================================================
# RUNTIME MODES
# ==============================================================================================
#
# mover_stop.sh
#     Check if mover is running. If so, warn users and stop it.
#
# mover_stop.sh --dry-run
#     Show mover state and what would happen. No signals sent.
#
# mover_stop.sh --status
#     Show mover state (running, PID, start time). Then exit.
#
# mover_stop.sh --log
#     Verbose output showing each step of the stop sequence.
#
# ==============================================================================================

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"

source "$SCRIPT_DIR/../load_config.sh"

parse_args "$@"

# ==============================================================================================
# ━━━ Setup ━━━
# ==============================================================================================
if [[ "$EUID" -ne 0 ]]; then
    error "Must be run as root — pkill on emhttp processes requires root"
    exit 1
fi

validate_unraid_cmd \
    "/usr/local/emhttp/plugins/dynamix/scripts/notify" \
    "" "" \
    "unRAID notify script" || warn "unRAID notify script not found — native notifications disabled"

validate_int MOVER_STOP_TIMEOUT "$MOVER_STOP_TIMEOUT"

acquire_lock

detect_hosts

[[ "$DRY_RUN" == true ]] && warn "DRY RUN — no changes will be made"

# ==============================================================================================
# ━━━ Status ━━━
# ==============================================================================================
if [[ "$SHOW_STATUS" == true ]]; then
    echo ""
    echo "━━━━━ $ICON_SUMMARY STATUS ━━━━━"
    echo "$ICON_HOST   Identity: $MY_ID ($LOCAL_SERVER_NAME)"
    echo "$ICON_MOVER  Timeout:  ${MOVER_STOP_TIMEOUT}s"
    echo "$ICON_GEAR   Dry Run:  $DRY_RUN"
    echo ""
    if pgrep -f "emhttp.*Mover" >/dev/null 2>&1; then
        MOVER_PID=$(pgrep -f "emhttp.*Mover" | head -1)
        MOVER_START=$(ps -o lstart= -p "$MOVER_PID" 2>/dev/null | xargs)
        echo "  $ICON_MOVER Mover: RUNNING (PID $MOVER_PID)"
        [[ -n "$MOVER_START" ]] && echo "  $ICON_TIME  Started: $MOVER_START"
    else
        echo "  $ICON_MOVER Mover: not running"
    fi
    echo "━━━━━━━━━━━━━━━━━━━━━━━"
    exit 0
fi

# ==============================================================================================
# ━━━ Mover Stop ━━━
# ==============================================================================================
START=$(date +%s)

if ! pgrep -f "emhttp.*Mover" >/dev/null 2>&1; then
    echo "Mover is not running — nothing to do"
    exit 0
fi

MOVER_PID=$(pgrep -f "emhttp.*Mover" | head -1)
warn "Mover is running (PID $MOVER_PID) — stopping in ${MOVER_STOP_TIMEOUT}s"

# ── Warn users via wall ───────────────────────────────────────────────────────────────────────
if [[ "$DRY_RUN" == false ]]; then
    wall "$ICON_WARN $MY_ID ($LOCAL_SERVER_NAME) — unRAID Mover stopping in ${MOVER_STOP_TIMEOUT}s"
    echo "Wall message sent — waiting ${MOVER_STOP_TIMEOUT}s..."
    sleep "$MOVER_STOP_TIMEOUT"
else
    warn "DRY RUN — would send wall warning and wait ${MOVER_STOP_TIMEOUT}s"
fi

# ── SIGTERM — graceful stop ───────────────────────────────────────────────────────────────────
if [[ "$DRY_RUN" == true ]]; then
    warn "DRY RUN — would send SIGTERM to mover (PID $MOVER_PID)"
else
    log "Sending SIGTERM to mover (PID $MOVER_PID)..."
    pkill -TERM -f "emhttp.*Mover" 2>/dev/null || true
    sleep 5

    # Verify stopped after SIGTERM
    if ! pgrep -f "emhttp.*Mover" >/dev/null 2>&1; then
        warn "Mover stopped cleanly (SIGTERM) ✅"
    else
        # ── SIGKILL — forced stop ─────────────────────────────────────────────────────────────
        warn "Mover still running after SIGTERM — sending SIGKILL (may leave partial files)"
        pkill -KILL -f "emhttp.*Mover" 2>/dev/null || true
        sleep 2

        # Final verify
        if pgrep -f "emhttp.*Mover" >/dev/null 2>&1; then
            error "Mover still running after SIGKILL — manual intervention needed"
            notify "Mover stop failed on $(hostname) ($MY_ID) — process unkillable" \
                "Mover Stop" "warning"
            exit 1
        else
            warn "Mover force-stopped (SIGKILL) — check for partial files on cache"
        fi
    fi
fi

END=$(date +%s)

# ==============================================================================================
# ━━━ Summary ━━━
# ==============================================================================================
echo ""
echo "━━━━━ $ICON_SUMMARY MOVER STOP SUMMARY ━━━━━"
echo "$ICON_HOST   Identity: $MY_ID ($LOCAL_SERVER_NAME)"
echo "$ICON_MOVER  Timeout:  ${MOVER_STOP_TIMEOUT}s"
echo "$ICON_TIME   Duration: $(format_duration $(( END - START )))"
echo ""

if [[ "$DRY_RUN" == true ]]; then
    warn "DRY RUN — no changes made"
else
    echo "$ICON_DONE Status: done — mover stopped ✅"
fi
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"