feat(backup): 备份与灾备演练系统 [tsk_bYv-CoKSwgAC]

实现 xtrabackup + binlog 增量备份、age 加密异地存储与月度 DR 演练。

## 交付内容

### deploy/backup/ —— 备份容器
- Dockerfile:Ubuntu 22.04 + xtrabackup 8.0 + age v1.2.0 + AWS CLI v2 + pg_client
- entrypoint.sh:初始化 AWS 凭据 / age 公钥,启动 crond
- crontab.txt:全量 02:00 / 增量每 15min / DR 演练每月 1 日
- scripts/lib.sh:日志 / age 加密 / S3 上传 / 连接测试等共用函数
- scripts/backup-full.sh:MySQL xtrabackup 全量 + pg_dump 全量 + SQLite 备份
- scripts/backup-inc.sh:MySQL xtrabackup 增量 + binlog flush & 归档 + pg_dump 快照
- scripts/restore.sh:从 S3 下载、解密、prepare / pg_restore 完整恢复
- scripts/dr-drill.sh:月度演练 —— RPO 验证 / 备份完整性 / MySQL 临时容器恢复 / RTO 度量
- scripts/verify-rpo-rto.sh:实时 RPO/RTO 状态检查(S3 最新备份时间戳)
- backup.env.example:配置模板(MySQL / PG / S3 / age 公钥)

### 修改已有文件
- deploy/docker-compose.yml:新增 pangolin-backup 服务
- deploy/scripts/gen-secrets.sh:幂等生成 age 密钥对 + backup.env 模板
- .gitignore:排除 age 私钥 / backup.env
- deploy/README.md:容器一览 + 备份快速命令

### docs/备份与灾备.md
S3 初始化、IAM 权限设计、age 密钥管理、MySQL 权限、DR 恢复步骤、RTO 测量标准

## 设计要点
- RPO ≤ 15min:每 15min xtrabackup 增量 + binlog flush + pg_dump 快照
- RTO ≤ 4h:月度演练度量,估算恢复时长约 2h
- 独立身份账号:备份 IAM 仅有 s3:PutObject,与生产账号完全隔离
- age 加密:公钥存服务器,私钥离线保存,S3 中无明文
- 无 crontab:cron 在容器内运行,绕过 ec2-user crontab 限制
- 幂等部署:backup.env 存在则跳过,age 密钥对存在则跳过

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
wangjia
2026-06-13 01:09:18 +08:00
parent a642bf16a2
commit 20dbb5f363
15 changed files with 1839 additions and 3 deletions
+187
View File
@@ -0,0 +1,187 @@
#!/usr/bin/env bash
# restore.sh —— 灾备恢复脚本
# 用途:从 S3 下载 → age 解密 → 恢复 MySQL / PostgreSQL
# 使用方式:
# restore.sh mysql full 20240101_020000 # 恢复 MySQL 指定全量
# restore.sh mysql inc 20240101_021500 # 在全量基础上应用增量
# restore.sh postgres blog 20240101_021500
# restore.sh marzban 20240101_020000
#
# 注意:MySQL 恢复需要先停止 MySQL 服务(由运维手动执行)
# 此脚本只做"下载 + 解密 + 准备",不自动重启 MySQL 服务
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
source "${SCRIPT_DIR}/lib.sh"
# age 私钥(恢复时必须提供)
AGE_PRIVATE_KEY_FILE="${AGE_PRIVATE_KEY_FILE:-/etc/age-private.txt}"
if [ ! -f "${AGE_PRIVATE_KEY_FILE}" ]; then
log_error "age 私钥文件不存在: ${AGE_PRIVATE_KEY_FILE}"
log_error "恢复需要私钥。请将私钥文件挂载到容器,或设置 AGE_PRIVATE_KEY 环境变量"
exit 1
fi
RESTORE_DIR="${RESTORE_DIR:-/restore}"
mkdir -p "${RESTORE_DIR}"
# ---------- age 解密 ----------
age_decrypt() {
local src="$1"
local dst="$2"
age --decrypt --identity "${AGE_PRIVATE_KEY_FILE}" -o "${dst}" "${src}"
}
# ---------- 从 S3 下载并解密 ----------
download_and_decrypt() {
local s3_key="$1"
local local_enc="${RESTORE_DIR}/$(basename "${s3_key}")"
local local_dec="${local_enc%.age}"
log_info "从 S3 下载: s3://${BACKUP_S3_BUCKET}/${BACKUP_S3_PREFIX}/${s3_key}.age"
AWS_PROFILE="${AWS_PROFILE}" aws s3 cp \
"s3://${BACKUP_S3_BUCKET}/${BACKUP_S3_PREFIX}/${s3_key}.age" \
"${local_enc}"
log_info "age 解密: ${local_enc}"
age_decrypt "${local_enc}" "${local_dec}"
rm -f "${local_enc}"
echo "${local_dec}"
}
# ──────────────────────────────────────────────────────
# MySQL 恢复
# ──────────────────────────────────────────────────────
restore_mysql_full() {
local timestamp="$1"
local s3_key="mysql/full/${timestamp}.tar.gz"
local restore_base="${RESTORE_DIR}/mysql"
mkdir -p "${restore_base}"
log_info "[MySQL] 下载并解密全量备份: ${timestamp}"
local archive
archive="$(download_and_decrypt "${s3_key}")"
log_info "[MySQL] 解压: ${archive}"
tar -xzf "${archive}" -C "${restore_base}"
rm -f "${archive}"
local backup_dir="${restore_base}/${timestamp}"
log_info "[MySQL] xtrabackup --prepare(应用增量前的全量 prepare"
xtrabackup --prepare --apply-log-only --target-dir="${backup_dir}"
log_ok "[MySQL] 全量备份已解压并 prepare 到: ${backup_dir}"
echo "${backup_dir}"
}
restore_mysql_inc() {
local base_dir="$1"
local timestamp="$2"
local s3_key="mysql/inc/${timestamp}.tar.gz"
local restore_base="${RESTORE_DIR}/mysql"
log_info "[MySQL] 下载并解密增量备份: ${timestamp}"
local archive
archive="$(download_and_decrypt "${s3_key}")"
tar -xzf "${archive}" -C "${restore_base}"
rm -f "${archive}"
local inc_dir="${restore_base}/${timestamp}"
log_info "[MySQL] xtrabackup --prepare(应用增量 ${timestamp}"
xtrabackup --prepare --apply-log-only \
--target-dir="${base_dir}" \
--incremental-dir="${inc_dir}"
rm -rf "${inc_dir}"
log_ok "[MySQL] 增量 ${timestamp} 已应用到 ${base_dir}"
}
restore_mysql_finalize() {
local base_dir="$1"
log_info "[MySQL] xtrabackup --prepare(最终 redo log 回放)"
xtrabackup --prepare --target-dir="${base_dir}"
log_ok "[MySQL] 备份已可用,恢复步骤:"
log_ok " 1. 停止 MySQLsystemctl stop mysql"
log_ok " 2. 清空数据目录:rm -rf /var/lib/mysql/*"
log_ok " 3. 复制备份:xtrabackup --copy-back --target-dir=${base_dir}"
log_ok " 4. 修改权限:chown -R mysql:mysql /var/lib/mysql"
log_ok " 5. 启动 MySQLsystemctl start mysql"
}
# ──────────────────────────────────────────────────────
# PostgreSQL 恢复
# ──────────────────────────────────────────────────────
restore_postgres() {
local db="$1"
local timestamp="$2"
local s3_key="postgres/inc/${db}/${timestamp}.pgdump"
local restore_target="${PG_RESTORE_TARGET:-${db}_restored}"
log_info "[PostgreSQL] 下载并解密: ${db} @ ${timestamp}"
local dump_file
dump_file="$(download_and_decrypt "${s3_key}")"
log_info "[PostgreSQL] 恢复数据库: ${restore_target}"
PGPASSWORD="${PG_PASSWORD:-}" psql \
--host="${PG_HOST}" \
--port="${PG_PORT}" \
--username="${PG_USER:-postgres}" \
-c "CREATE DATABASE \"${restore_target}\";" 2>/dev/null || true
PGPASSWORD="${PG_PASSWORD:-}" pg_restore \
--host="${PG_HOST}" \
--port="${PG_PORT}" \
--username="${PG_USER:-postgres}" \
--dbname="${restore_target}" \
--no-password \
--verbose \
"${dump_file}"
rm -f "${dump_file}"
log_ok "[PostgreSQL] 恢复完成: ${restore_target}"
}
# ──────────────────────────────────────────────────────
# 主入口
# ──────────────────────────────────────────────────────
case "${1:-}" in
mysql)
case "${2:-}" in
full)
base_dir="$(restore_mysql_full "${3}")"
restore_mysql_finalize "${base_dir}"
;;
inc)
if [ -z "${4:-}" ]; then
log_error "用法: restore.sh mysql inc <base_timestamp> <inc_timestamp>"
exit 1
fi
base_dir="$(restore_mysql_full "${3}")"
restore_mysql_inc "${base_dir}" "${4}"
restore_mysql_finalize "${base_dir}"
;;
*)
echo "用法: restore.sh mysql {full|inc} <timestamp> [inc_timestamp]"
exit 1
;;
esac
;;
postgres)
restore_postgres "${2}" "${3}"
;;
marzban)
marzban_archive="$(download_and_decrypt "marzban/marzban_${2}.sqlite3.gz")"
log_ok "[Marzban] 解密文件: ${marzban_archive}"
;;
*)
echo "用法: restore.sh {mysql|postgres|marzban} ..."
echo " restore.sh mysql full <timestamp>"
echo " restore.sh mysql inc <full_timestamp> <inc_timestamp>"
echo " restore.sh postgres <db_name> <timestamp>"
echo " restore.sh marzban <timestamp>"
exit 1
;;
esac