feat: bin/systemd_deploy.sh 一键部署脚本

work #05 (2026-07-03):Stop hook 反馈 work #04 结尾'目标达成'是错的
预测,不是现状。timer/service 没真的跑 = 数据没真的进 PG。

work #01-04 全是代码/配置改动,没可执行 deploy 路径;user 每次手动
cp + daemon-reload + enable 5 个 unit 是出错温床。

修复:写 bin/systemd_deploy.sh,必须 sudo 跑,幂等,显示 plan → 等
用户确认 → 执行(拷贝 + 删孤儿 + reload + enable 新 timer + 验证)。

下一步:user 跑 sudo bash bin/systemd_deploy.sh 真把 unit 部署到
/etc,daily_check drift 才能归零,sync 目标才进入可观察达成路径。

重要:脚本就绪 ≠ 目标达成;脚本是必要非充分条件。

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
gao
2026-07-03 11:44:33 +08:00
parent cf45f98a8a
commit 46ddf8e171
2 changed files with 261 additions and 0 deletions
+185
View File
@@ -0,0 +1,185 @@
#!/bin/bash
# market_sync systemd 一键部署脚本
#
# 用途:把 bin/systemd/*.service 和 *.timer 同步到 /etc/systemd/system/
# 解决 work #04 检测到的 5 处 drift。
#
# 运行:sudo bash bin/systemd_deploy.sh
#
# 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="/home/gao/Development/quant_home/market_sync"
REPO_UNITS_DIR="$PROJECT_ROOT/bin/systemd"
ETC_UNITS_DIR="/etc/systemd/system"
# ── 0. 前置检查 ─────────────────────────────────────────────────────────────
if [ "$(id -u)" -ne 0 ]; then
echo "❌ 必须 sudo 运行:sudo bash $0"
exit 1
fi
if [ ! -d "$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
echo "Repo units: ${#REPO_UNITS[@]}"
echo "/etc units: ${#ETC_UNITS[@]}"
echo
if [ ${#TO_COPY[@]} -eq 0 ] && [ ${#TO_REMOVE[@]} -eq 0 ]; then
echo "✅ 无 drift 需要修复。无需执行。"
exit 0
fi
if [ ${#TO_COPY[@]} -gt 0 ]; then
echo "📋 将要拷贝 ($(echo "${TO_COPY[@]}" | tr ' ' '\n' | wc -l) 个):"
for u in "${TO_COPY[@]}"; do
echo " cp bin/systemd/$u → /etc/systemd/system/$u"
done
echo
fi
if [ ${#TO_RESTART_SVC[@]} -gt 0 ]; then
echo "🔄 将要重启 service ($(echo "${TO_RESTART_SVC[@]}" | tr ' ' '\n' | wc -l) 个):"
for s in "${TO_RESTART_SVC[@]}"; do
echo " systemctl reset-failed $s.service"
done
echo
fi
if [ ${#TO_REMOVE[@]} -gt 0 ]; then
echo "🗑️ 将要删除 etc 中的孤儿 ($(echo "${TO_REMOVE[@]}" | tr ' ' '\n' | wc -l) 个):"
for u in "${TO_REMOVE[@]}"; do
echo " rm /etc/systemd/system/$u"
done
echo
fi
# ── 3. 等待确认 ────────────────────────────────────────────────────────────
read -p "确认执行?[y/N] " -n 1 -r
echo
if [[ ! $REPLY =~ ^[Yy]$ ]]; then
echo "已取消。"
exit 0
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. 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 ${s}.service (没自动 restart — 由 timer 自然触发)"
fi
done
# 4e. 启用新 timer(如果有)
for u in "${TO_COPY[@]}"; do
if [[ "$u" == *.timer ]]; then
timer="${u%.timer}"
if systemctl list-unit-files "${timer}.timer" 2>/dev/null | grep -q "${timer}.timer"; then
if ! systemctl is-enabled "${timer}.timer" 2>/dev/null | grep -q enabled; then
systemctl enable "${timer}.timer"
echo " enable ${timer}.timer"
fi
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
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