Files
pangolin/deploy/backup/scripts/verify-rpo-rto.sh
T
wangjia 20dbb5f363 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>
2026-06-13 01:09:18 +08:00

168 lines
6.4 KiB
Bash

#!/usr/bin/env bash
# verify-rpo-rto.sh —— 实时 RPO/RTO 状态检查
# 用法:
# verify-rpo-rto.sh # 完整检查并打印结果
# verify-rpo-rto.sh --status-only # 仅打印摘要(容器启动时调用)
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
source "${SCRIPT_DIR}/lib.sh"
STATUS_ONLY="${1:-}"
log_info "RPO/RTO 状态检查"
RPO_TARGET_SECONDS=900 # 15 分钟
RTO_TARGET_HOURS=4
PASS=0
WARN=0
FAIL=0
check() {
local status="$1"
local msg="$2"
case "${status}" in
pass) PASS=$(( PASS + 1 )); log_ok "${msg}" ;;
warn) WARN=$(( WARN + 1 )); log_warn " ⚠️ ${msg}" ;;
fail) FAIL=$(( FAIL + 1 )); log_error "${msg}" ;;
esac
}
# ──────────────────────────────────────────────────────
# 1. 检查 S3 最新增量备份的时间
# ──────────────────────────────────────────────────────
check_latest_backup_age() {
local service="$1"
local s3_prefix="$2"
local latest
latest="$(AWS_PROFILE="${AWS_PROFILE}" aws s3 ls \
"s3://${BACKUP_S3_BUCKET}/${BACKUP_S3_PREFIX}/${s3_prefix}/" \
--recursive 2>/dev/null \
| sort | tail -1 | awk '{print $1, $2}' || echo "")"
if [ -z "${latest}" ]; then
check fail "${service}: S3 中无备份"
return
fi
local last_date last_time
last_date=$(echo "${latest}" | awk '{print $1}')
last_time=$(echo "${latest}" | awk '{print $2}')
local last_ts
last_ts="$(date -d "${last_date} ${last_time}" +%s 2>/dev/null \
|| date -j -f '%Y-%m-%d %H:%M:%S' "${last_date} ${last_time}" +%s 2>/dev/null \
|| echo 0)"
local now
now=$(date +%s)
local gap=$(( now - last_ts ))
local gap_min=$(( gap / 60 ))
if [ "${gap}" -le "${RPO_TARGET_SECONDS}" ]; then
check pass "${service}: 最新备份距今 ${gap_min}min (RPO ≤ 15min ✓)"
elif [ "${gap}" -le $(( RPO_TARGET_SECONDS * 2 )) ]; then
check warn "${service}: 最新备份距今 ${gap_min}min (接近 RPO 限制)"
else
check fail "${service}: 最新备份距今 ${gap_min}min (超出 RPO 15min 限制)"
fi
}
# ──────────────────────────────────────────────────────
# 2. 检查 S3 最新全量备份时间(应为 < 25 小时)
# ──────────────────────────────────────────────────────
check_full_backup_freshness() {
local service="$1"
local s3_prefix="$2"
local latest
latest="$(AWS_PROFILE="${AWS_PROFILE}" aws s3 ls \
"s3://${BACKUP_S3_BUCKET}/${BACKUP_S3_PREFIX}/${s3_prefix}/" \
2>/dev/null | sort | tail -1 | awk '{print $1, $2}' || echo "")"
if [ -z "${latest}" ]; then
check fail "${service} 全量: S3 中无全量备份"
return
fi
local last_date last_time
last_date=$(echo "${latest}" | awk '{print $1}')
last_time=$(echo "${latest}" | awk '{print $2}')
local last_ts
last_ts="$(date -d "${last_date} ${last_time}" +%s 2>/dev/null \
|| date -j -f '%Y-%m-%d %H:%M:%S' "${last_date} ${last_time}" +%s 2>/dev/null \
|| echo 0)"
local now
now=$(date +%s)
local gap_hours=$(( (now - last_ts) / 3600 ))
if [ "${gap_hours}" -le 25 ]; then
check pass "${service} 全量: 最近 ${gap_hours}h 内有全量备份"
else
check fail "${service} 全量: 上次全量备份距今 ${gap_hours}h (> 25h)"
fi
}
# ──────────────────────────────────────────────────────
# 3. 检查 DR 演练报告(最新演练是否在 35 天内)
# ──────────────────────────────────────────────────────
check_dr_drill_freshness() {
local latest
latest="$(AWS_PROFILE="${AWS_PROFILE}" aws s3 ls \
"s3://${BACKUP_S3_BUCKET}/${BACKUP_S3_PREFIX}/dr-reports/" \
2>/dev/null | sort | tail -1 | awk '{print $1, $2}' || echo "")"
if [ -z "${latest}" ]; then
check warn "DR 演练: S3 中无演练报告(首次部署?)"
return
fi
local last_date last_time
last_date=$(echo "${latest}" | awk '{print $1}')
last_time=$(echo "${latest}" | awk '{print $2}')
local last_ts
last_ts="$(date -d "${last_date} ${last_time}" +%s 2>/dev/null \
|| date -j -f '%Y-%m-%d %H:%M:%S' "${last_date} ${last_time}" +%s 2>/dev/null \
|| echo 0)"
local now
now=$(date +%s)
local gap_days=$(( (now - last_ts) / 86400 ))
if [ "${gap_days}" -le 35 ]; then
check pass "DR 演练: 上次演练距今 ${gap_days}"
else
check warn "DR 演练: 上次演练距今 ${gap_days} 天 (> 35 天,请检查)"
fi
}
# ──────────────────────────────────────────────────────
# 执行检查
# ──────────────────────────────────────────────────────
check_latest_backup_age "MySQL-增量" "mysql/inc"
check_latest_backup_age "PG-增量" "postgres/inc"
check_full_backup_freshness "MySQL" "mysql/full"
check_full_backup_freshness "PostgreSQL" "postgres/full"
check_dr_drill_freshness
# ──────────────────────────────────────────────────────
# 汇总
# ──────────────────────────────────────────────────────
echo ""
log_info "RPO/RTO 检查汇总"
log_info " 通过: ${PASS} 警告: ${WARN} 失败: ${FAIL}"
log_info " RPO 目标: ≤ 15min | RTO 目标: ≤ ${RTO_TARGET_HOURS}h"
if [ "${FAIL}" -gt 0 ]; then
log_error "状态: 不达标 ❌"
exit 1
elif [ "${WARN}" -gt 0 ]; then
log_warn "状态: 警告 ⚠️"
exit 0
else
log_ok "状态: 达标 ✅"
exit 0
fi