#!/bin/bash
# ==============================================================================================
# ================================= inotify Tuning ============================================
# ==============================================================================================
#
# PURPOSE
# ─────────────────────────────────────────────────────────────────────────────
# Raises Linux inotify limits at array start to prevent exhaustion across the
# container stack. Run once at array start via ARRAY_START_SCRIPTS. Settings
# are lost on reboot — this script reapplies them on every array start.
#
# Must run FIRST in ARRAY_START_SCRIPTS before any containers start — containers
# inherit inotify limits at launch, not dynamically. Running this after Code-Server
# starts requires a docker restart to pick up the new values.
#
# ==============================================================================================
# DESIGN PRINCIPLES
# ==============================================================================================
#
# Three inotify Limits
#   max_user_instances  — max independent inotify fd objects per user; each container
#                         calling inotify_init() consumes one. Default 128 — exhausted
#                         quickly with 20+ active containers.
#
#   max_user_watches    — SHARED budget across ALL users and containers on the system.
#                         Each watched file or directory costs one watch. Default 8192 —
#                         VSCode alone needs 50K–200K for large workspaces. Combined
#                         usage of Sonarr, Radarr, Lidarr, Emby, Nextcloud, Code-Server
#                         easily exceeds 512K on a busy server.
#
#   max_queued_events   — max events buffered before the kernel drops them. Low value =
#                         events silently lost during high-activity bursts. Default 16384.
#
# Why 1M Watches
#   Raising max_user_watches to 1048576 (1M) gives sufficient headroom for all
#   containers combined — safe on 128GB RAM (~128MB kernel use for the pool).
#
# Idempotent Per-Setting
#   Each sysctl value is read before writing. Only changed if different from target —
#   no-op on boots where limits are already correct.
#
# ==============================================================================================
# OPERATIONAL SAFEGUARDS
# ==============================================================================================
#
# Root Required
#   sysctl writes require root.
#
# Single Instance Lock
#   acquire_lock prevents duplicate runs at array start.
#
# Silent on Success
#   Runs every boot — no noise when already correct.
#
# ==============================================================================================
# CONFIGURATION
# ==============================================================================================
#
# master.conf
#
#   INOTIFY_MAX_INSTANCES
#       Max inotify fd objects per user. (default: 1024)
#
#   INOTIFY_MAX_WATCHES
#       Max watched files/dirs shared across all users and containers. (default: 1048576)
#
#   INOTIFY_MAX_QUEUED_EVENTS
#       Max events buffered before kernel drops them. (default: 32768)
#
# ==============================================================================================
# RUNTIME MODES
# ==============================================================================================
#
# inotify_tuning.sh
#     Apply inotify limits. No-op per setting if already at target.
#
# inotify_tuning.sh --dry-run
#     Show current vs target for each limit. No sysctl writes.
#
# inotify_tuning.sh --status
#     Show current vs target, active instance count, and top consumers by PID.
#
# inotify_tuning.sh --log
#     Verbose output — show each sysctl check and result.
#
# ==============================================================================================

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 — sysctl writes require root"
    exit 1
fi

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

acquire_lock

if ! command -v docker &>/dev/null; then
    error "Docker command not found"
    exit 1
fi

detect_hosts

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

# ==============================================================================================
# ━━━ Status ━━━
# ==============================================================================================
if [[ "$SHOW_STATUS" == true ]]; then
    echo ""
    echo "━━━━━ $ICON_SUMMARY INOTIFY STATUS ━━━━━"
    echo "$ICON_HOST Identity:  $MY_ID ($LOCAL_SERVER_NAME)"
    echo ""

    echo "━━━ Kernel Limits ━━━"
    CURRENT_INSTANCES=$(sysctl -n fs.inotify.max_user_instances 2>/dev/null || echo "?")
    CURRENT_WATCHES=$(sysctl  -n fs.inotify.max_user_watches    2>/dev/null || echo "?")
    CURRENT_EVENTS=$(sysctl   -n fs.inotify.max_queued_events   2>/dev/null || echo "?")

    for label in "max_user_instances  current=$CURRENT_INSTANCES target=$INOTIFY_MAX_INSTANCES" \
                 "max_user_watches    current=$CURRENT_WATCHES  target=$INOTIFY_MAX_WATCHES" \
                 "max_queued_events   current=$CURRENT_EVENTS   target=$INOTIFY_MAX_QUEUED_EVENTS"; do
        echo "  $label"
    done

    echo ""
    echo "━━━ Active Instances ━━━"
    USED_INSTANCES=$(find /proc/*/fd -lname 'anon_inode:inotify' 2>/dev/null | wc -l)
    USED_INSTANCES="${USED_INSTANCES//[^0-9]/}"
    echo "  Instances in use: ${USED_INSTANCES:-0} / $CURRENT_INSTANCES"
    if [[ "$CURRENT_INSTANCES" -gt 0 ]]; then
        PCT=$(( ${USED_INSTANCES:-0} * 100 / CURRENT_INSTANCES ))
        echo "  Utilisation: ${PCT}%"
    fi

    echo ""
    echo "━━━ Top Consumers ━━━"
    find /proc/*/fd -lname 'anon_inode:inotify' 2>/dev/null | \
        awk -F/ '{print $3}' | sort | uniq -c | sort -rn | head -10 | \
        while read -r count pid; do
            cmd=$(cat /proc/"$pid"/comm 2>/dev/null || echo "?")
            cgroup=$(cat /proc/"$pid"/cgroup 2>/dev/null | \
                grep docker | grep -o '[a-f0-9]\{12\}' | head -1 || echo "")
            if [[ -n "$cgroup" ]]; then
                label="[docker:${cgroup}] $cmd"
            else
                label="[host] $cmd"
            fi
            echo "  ${count} instances — $label (PID $pid)"
        done | head -10

    echo ""
    echo "━━━ VSCode / Code-Server ━━━"
    echo "  If VSCode shows 'unable to watch for file changes':"
    echo "  1. Verify max_user_watches target is set high enough"
    echo "  2. Check total watches used: cat /proc/sys/fs/inotify/max_user_watches"
    echo "  3. After any limit change: docker restart Code-Server"
    echo "     (running containers inherit limits at start, not dynamically)"
    echo "━━━━━━━━━━━━━━━━━━━━━━━"
    exit 0
fi

# ==============================================================================================
# ━━━ Apply Settings ━━━
# ==============================================================================================
CHANGED=0
FAILED=0

apply_sysctl() {
    local key="$1" value="$2"
    local current
    current=$(sysctl -n "$key" 2>/dev/null || echo 0)

    if [[ "$current" -eq "$value" ]]; then
        log "$key = $value (already correct)"
        return 0
    fi

    if [[ "$DRY_RUN" == true ]]; then
        warn "DRY RUN — would set $key = $value (currently $current)"
        return 0
    fi

    if sysctl -w "${key}=${value}" >/dev/null 2>&1; then
        warn "Set $key = $value (was $current)"
        (( CHANGED++ ))
    else
        error "Failed to set $key = $value"
        (( FAILED++ ))
    fi
}

apply_sysctl "fs.inotify.max_user_instances" "$INOTIFY_MAX_INSTANCES"
apply_sysctl "fs.inotify.max_user_watches"   "$INOTIFY_MAX_WATCHES"
apply_sysctl "fs.inotify.max_queued_events"  "$INOTIFY_MAX_QUEUED_EVENTS"
apply_sysctl "vm.overcommit_memory"          "1"   # Redis: prevents background save failures under low memory

# ==============================================================================================
# ━━━ Summary ━━━
# ==============================================================================================
if [[ "$FAILED" -gt 0 ]]; then
    echo ""
    echo "━━━━━ $ICON_SUMMARY INOTIFY TUNING SUMMARY ━━━━━"
    echo "$ICON_HOST Identity: $MY_ID ($LOCAL_SERVER_NAME)"
    echo "$ICON_ERROR $FAILED setting(s) failed to apply"
    notify "inotify tuning failed on $(hostname) ($MY_ID) — $FAILED setting(s) could not be applied" \
        "inotify Tuning" "warning"
    echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
    exit 1
elif [[ "$CHANGED" -gt 0 ]]; then
    echo ""
    echo "━━━━━ $ICON_SUMMARY INOTIFY TUNING SUMMARY ━━━━━"
    echo "$ICON_HOST Identity:          $MY_ID ($LOCAL_SERVER_NAME)"
    echo "  max_user_instances:  $(sysctl -n fs.inotify.max_user_instances 2>/dev/null)"
    echo "  max_user_watches:    $(sysctl -n fs.inotify.max_user_watches   2>/dev/null)"
    echo "  max_queued_events:   $(sysctl -n fs.inotify.max_queued_events  2>/dev/null)"
    echo ""
    warn "$CHANGED setting(s) updated"
    if [[ "$CHANGED" -gt 0 ]]; then
        warn "If Code-Server is running: docker restart Code-Server"
        warn "Running containers inherit limits at start — restart picks up new values"
    fi
    echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
else
    echo "inotify limits already correct ✅"
fi

exit 0