#!/bin/bash
# ==============================================================================================
# ================================= Mover Stop =================================================
# ==============================================================================================
# Safely stops the unRAID mover process with a warning before halting.
# Warns all logged-in users via wall message, waits the configured timeout, then stops.
#
# ── WHEN TO USE ───────────────────────────────────────────────────────────────────────────────
#   - Before a planned reboot when mover is running mid-cycle
#   - Before disk replacement or array operations that need mover stopped
#   - Before rsync — mover and rsync simultaneously moving the same files causes corruption
#   - Called automatically by maintenance scripts that need the mover stopped first
#
# ── STOP SEQUENCE ─────────────────────────────────────────────────────────────────────────────
#   1. Check if mover is running — exit cleanly if not
#   2. Broadcast wall warning to all logged-in users
#   3. Wait MOVER_STOP_TIMEOUT seconds (default 30) — gives active sessions a chance to note it
#   4. Send SIGTERM — mover can complete its current file operation before exiting
#   5. Wait 5 seconds for graceful exit
#   6. Verify stopped — if still running send SIGKILL (force)
#   7. Final verify — error if still running after SIGKILL
#
# ── SIGTERM vs SIGKILL ────────────────────────────────────────────────────────────────────────
# SIGTERM first — allows mover to finish the file it is currently moving (no partial files).
# SIGKILL only as fallback — forces immediate stop (may leave partial files on cache or array).
#
# ── SAFEGUARDS ────────────────────────────────────────────────────────────────────────────────
#   acquire_lock     — prevents concurrent stop attempts racing each other
#   Root check       — pkill on emhttp processes requires root
#   validate_unraid  — notify validated before use
#   SIGTERM → verify → SIGKILL sequence — graceful then forced
#   Final verify     — confirms mover actually stopped
#   Silent on clean  — mover not running = log() only, no output ✅
#
# ── CONFIGURATION (master.conf) ───────────────────────────────────────────────────────────────
#   MOVER_STOP_TIMEOUT — seconds to warn users before stopping (default 30)
#
# ── USAGE ─────────────────────────────────────────────────────────────────────────────────────
#   mover_stop.sh              — stop mover with configured timeout
#   mover_stop.sh --dry-run    — show what would happen
#   mover_stop.sh --status     — show mover state
#   mover_stop.sh --log        — verbose output
# ==============================================================================================

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