market_sync/deploy/systemd/deploy.sh

#!/bin/bash
# market_sync systemd 一键部署脚本
#
# 用途：把 deploy/systemd/units/*.service 和 *.timer 同步到 /etc/systemd/system/，
#       并自动启用 timer、处理 worker 服务状态。
#
# 运行：sudo bash deploy/systemd/deploy.sh
#      sudo bash deploy/systemd/deploy.sh --yes    # 跳过确认
#
# 设计原则：
#   - 必须 sudo（写 /etc/systemd/system/ + daemon-reload）
#   - 幂等：重复运行无副作用
#   - 显示 plan → 等待确认 → 执行
#   - 失败立即中止，不留半套状态

set -e

PROJECT_ROOT="$(cd "$(dirname "$0")/../.." && pwd)"
REPO_UNITS_DIR="$PROJECT_ROOT/deploy/systemd/units"
ETC_UNITS_DIR="/etc/systemd/system"
SKIP_CONFIRM=false

# ── 0. 前置检查 ─────────────────────────────────────────────────────────────
if [ "$(id -u)" -ne 0 ]; then
  echo "❌ 必须 sudo 运行：sudo bash $0"
  exit 1
fi

if [ "${1:-}" = "--yes" ]; then
  SKIP_CONFIRM=true
fi

if [ ! -d "$REPO_UNITS_DIR" ]; then
  echo "❌ repo unit 目录不存在: $REPO_UNITS_DIR"
  exit 1
fi

# ── 1. 计算 plan ────────────────────────────────────────────────────────────
declare -a TO_COPY=()        # repo→etc 拷贝
declare -a TO_REMOVE=()      # etc 中孤儿（repo 已删）
declare -a TO_RESTART_SVC=() # service 文件变了需要 daemon-reload + restart

# repo 中所有 market-sync* unit
mapfile -t REPO_UNITS < <(find "$REPO_UNITS_DIR" -maxdepth 1 -type f \( -name "*.service" -o -name "*.timer" \) -printf '%f\n' | sort)
# /etc 中所有 market-sync* unit
mapfile -t ETC_UNITS < <(find "$ETC_UNITS_DIR" -maxdepth 1 -type f \( -name "market-sync*.service" -o -name "market-sync*.timer" \) -printf '%f\n' | sort 2>/dev/null || true)

# drift 1: repo 有 /etc 没装
for u in "${REPO_UNITS[@]}"; do
  if [ ! -f "$ETC_UNITS_DIR/$u" ]; then
    TO_COPY+=("$u")
  fi
done

# drift 2: 两边都有但内容不一致
for u in "${REPO_UNITS[@]}"; do
  if [ -f "$ETC_UNITS_DIR/$u" ]; then
    if ! diff -q "$REPO_UNITS_DIR/$u" "$ETC_UNITS_DIR/$u" > /dev/null 2>&1; then
      TO_COPY+=("$u")
      if [[ "$u" == *.service ]]; then
        TO_RESTART_SVC+=("${u%.service}")
      fi
    fi
  fi
done

# drift 3: /etc 有 repo 没维护（孤儿）
for u in "${ETC_UNITS[@]}"; do
  found=0
  for r in "${REPO_UNITS[@]}"; do
    if [ "$r" = "$u" ]; then found=1; break; fi
  done
  if [ $found -eq 0 ]; then
    TO_REMOVE+=("$u")
  fi
done

# ── 2. 显示 plan ────────────────────────────────────────────────────────────
echo "============================================================"
echo "market_sync systemd deploy plan"
echo "============================================================"
echo "Repo units dir: $REPO_UNITS_DIR"
echo
echo "Repo units:    ${#REPO_UNITS[@]} 个"
echo "/etc units:    ${#ETC_UNITS[@]} 个"
echo

if [ ${#TO_COPY[@]} -eq 0 ] && [ ${#TO_REMOVE[@]} -eq 0 ]; then
  echo "✅ 无 drift 需要修复。"
else
  if [ ${#TO_COPY[@]} -gt 0 ]; then
    echo "📋 将要拷贝 (${#TO_COPY[@]} 个):"
    for u in "${TO_COPY[@]}"; do
      echo "    cp deploy/systemd/units/$u  →  /etc/systemd/system/$u"
    done
    echo
  fi

  if [ ${#TO_RESTART_SVC[@]} -gt 0 ]; then
    echo "🔄 将要处理 service (${#TO_RESTART_SVC[@]} 个):"
    for s in "${TO_RESTART_SVC[@]}"; do
      echo "    systemctl reset-failed $s.service"
    done
    echo
  fi

  if [ ${#TO_REMOVE[@]} -gt 0 ]; then
    echo "🗑️  将要删除 etc 中的孤儿 (${#TO_REMOVE[@]} 个):"
    for u in "${TO_REMOVE[@]}"; do
      echo "    rm /etc/systemd/system/$u"
    done
    echo
  fi
fi

# ── 3. 等待确认 ────────────────────────────────────────────────────────────
if [ "$SKIP_CONFIRM" = false ]; then
  read -p "确认执行？[y/N] " -n 1 -r
  echo
  if [[ ! $REPLY =~ ^[Yy]$ ]]; then
    echo "已取消。"
    exit 0
  fi
fi

# ── 4. 执行 ─────────────────────────────────────────────────────────────────
echo
echo "=== 执行 ==="

# 4a. cp 漂移的 unit
for u in "${TO_COPY[@]}"; do
  cp -v "$REPO_UNITS_DIR/$u" "$ETC_UNITS_DIR/$u"
done

# 4b. 删孤儿
for u in "${TO_REMOVE[@]}"; do
  rm -v "$ETC_UNITS_DIR/$u"
done

# 4c. reload systemd
echo
echo "=== systemctl daemon-reload ==="
systemctl daemon-reload

# 4d. 停用并 mask worker 服务（systemd 模式下不需要进程内 scheduler）
if systemctl is-enabled market-sync-worker.service >/dev/null 2>&1 || \
   systemctl is-active market-sync-worker.service >/dev/null 2>&1; then
  echo "=== 关闭 market-sync-worker.service（systemd 模式下由 timer 触发任务）==="
  systemctl stop market-sync-worker.service || true
  systemctl disable market-sync-worker.service || true
  systemctl mask market-sync-worker.service || true
fi

# 4e. reset-failed + restart 修改过的 service
for s in "${TO_RESTART_SVC[@]}"; do
  if systemctl is-enabled "${s}.service" 2>/dev/null | grep -q enabled; then
    systemctl reset-failed "${s}.service" || true
    echo "  reset-failed ${s}.service (由 timer 自然触发)"
  fi
done

# 4f. 启用所有 timer（幂等）
echo
echo "=== 启用 timers ==="
for u in "${REPO_UNITS[@]}"; do
  if [[ "$u" == *.timer ]]; then
    timer="${u%.timer}"
    if ! systemctl is-enabled "${timer}.timer" >/dev/null 2>&1; then
      systemctl enable "${timer}.timer"
      echo "  enable ${timer}.timer"
    else
      echo "  ${timer}.timer 已启用"
    fi
  fi
done

# ── 5. 验证 ────────────────────────────────────────────────────────────────
echo
echo "=== 验证 ==="
echo "Repo units:    ${#REPO_UNITS[@]}"
echo "/etc units:    $(find "$ETC_UNITS_DIR" -maxdepth 1 -type f \( -name 'market-sync*.service' -o -name 'market-sync*.timer' \) | wc -l)"

drift_count=0
for u in "${REPO_UNITS[@]}"; do
  if [ -f "$ETC_UNITS_DIR/$u" ]; then
    if ! diff -q "$REPO_UNITS_DIR/$u" "$ETC_UNITS_DIR/$u" > /dev/null 2>&1; then
      echo "  ❌ $u 仍有 drift"
      drift_count=$((drift_count + 1))
    fi
  else
    echo "  ❌ $u 仍未部署"
    drift_count=$((drift_count + 1))
  fi
done

# 验证 worker 已被 mask
if systemctl is-enabled market-sync-worker.service 2>/dev/null | grep -q masked; then
  echo "  ✅ market-sync-worker.service 已 mask（systemd 模式下不启用进程内 scheduler）"
else
  echo "  ⚠️  market-sync-worker.service 未被 mask，systemd 模式下可能双调度器重叠"
fi

echo
if [ $drift_count -eq 0 ]; then
  echo "✅ 所有 unit 已对齐，0 drift"
  echo
  echo "下一步：跑 .venv/bin/python bin/daily_sync_check.py --report-only 验证"
else
  echo "❌ 还有 $drift_count 处 drift，请检查"
  exit 1
fi