b5e27810fd
- scripts/backup_full.sh：容器内 mysqldump --single-transaction，gzip 落盘 db/backups/，保留 30 天；凭据 source docker/.env 不硬编码；实测备份成功 - scripts/restore_drill.sh：恢复到临时库 payroll_drill_* 并逐表核对行数 （16 张关键表），默认不 DROP、--drop-exec 才删——绝不覆盖生产库； 实测 16 表全 ✓。规避嵌套 shell 吞反引号（mysqladmin create/drop、 双引号包裹表名） - scripts/health_check.sh：六项检查（容器健康×2/磁盘水位/备份新鲜度/ Redis 探活/24h 登录失败阈值），PASS/WARN/FAIL 报告，退出码供监控； Redis 密码经宿主机 .env 验证（容器内无该环境变量），实测六项全 PASS - docs/备份恢复手册.md：备份/演练/生产恢复七步/定时 schtasks 两则， db/backups/ 已入 .gitignore Co-Authored-By: Claude Code <noreply@anthropic.com>
106 lines
3.6 KiB
Bash
106 lines
3.6 KiB
Bash
#!/usr/bin/env bash
|
||
# 运维健康检查 —— 容器/磁盘/备份新鲜度/登录异常（⑨ 输出一份可读报告）
|
||
#
|
||
# 用法：在项目根目录执行 bash scripts/health_check.sh
|
||
# 每项 PASS/WARN/FAIL，最后给出结论。WARN/FAIL 时退出码非零提示运维介入。
|
||
|
||
set -uo pipefail
|
||
|
||
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||
cd "$ROOT"
|
||
|
||
if [[ -f docker/.env ]]; then
|
||
# shellcheck disable=SC1091
|
||
source docker/.env
|
||
fi
|
||
|
||
ISSUES=0
|
||
report() { printf "%-10s %s\n" "$1" "$2"; }
|
||
warn() { report "WARN" "$1"; ISSUES=$((ISSUES+1)); }
|
||
fail() { report "FAIL" "$1"; ISSUES=$((ISSUES+1)); }
|
||
pass() { report "PASS" "$1"; }
|
||
|
||
echo "======== 衍水工资系统 健康检查 $(date '+%Y-%m-%d %H:%M:%S') ========"
|
||
|
||
# 1. 容器健康
|
||
for C in ys-mysql-dev ys-redis-dev; do
|
||
if ! docker inspect "$C" >/dev/null 2>&1; then
|
||
fail "容器 $C 不存在"
|
||
continue
|
||
fi
|
||
STATUS="$(docker inspect -f '{{.State.Health.Status}}' "$C" 2>/dev/null || echo none)"
|
||
RUNNING="$(docker inspect -f '{{.State.Running}}' "$C" 2>/dev/null)"
|
||
if [[ "$RUNNING" == "true" && "$STATUS" == "healthy" ]]; then
|
||
pass "容器 $C 运行中且健康"
|
||
elif [[ "$RUNNING" == "true" ]]; then
|
||
warn "容器 $C 运行中但健康检查=$STATUS"
|
||
else
|
||
fail "容器 $C 未运行"
|
||
fi
|
||
done
|
||
|
||
# 2. 磁盘水位
|
||
DISK_PCT="$(df -h "$ROOT" | awk 'NR==2 {gsub(/%/,"",$5); print $5}')"
|
||
if [[ -z "$DISK_PCT" ]]; then
|
||
warn "磁盘信息读取失败"
|
||
elif (( DISK_PCT < 80 )); then
|
||
pass "磁盘使用率 ${DISK_PCT}%（阈值 80%）"
|
||
elif (( DISK_PCT < 90 )); then
|
||
warn "磁盘使用率 ${DISK_PCT}%（建议清理）"
|
||
else
|
||
fail "磁盘使用率 ${DISK_PCT}%（高危，立即清理）"
|
||
fi
|
||
|
||
# 3. 备份新鲜度
|
||
BACKUP_DIR="$ROOT/db/backups"
|
||
LATEST="$(ls -t "$BACKUP_DIR"/payroll_*.sql.gz 2>/dev/null | head -1)"
|
||
if [[ -z "$LATEST" ]]; then
|
||
warn "未找到任何备份（应每日备份）"
|
||
else
|
||
AGE_H=$(( ($(date +%s) - $(stat -c %Y "$LATEST")) / 3600 ))
|
||
if (( AGE_H < 24 )); then
|
||
pass "最新备份 $(basename "$LATEST")，${AGE_H} 小时前"
|
||
elif (( AGE_H < 48 )); then
|
||
warn "最新备份已 ${AGE_H} 小时前（超过 24 小时）"
|
||
else
|
||
fail "最新备份已 ${AGE_H} 小时前（备份任务可能已停）"
|
||
fi
|
||
fi
|
||
|
||
# 4. Redis 存活（密码经宿主 docker/.env，不经命令行明文参数）
|
||
if [[ -n "${REDIS_PASSWORD:-}" ]]; then
|
||
if docker exec ys-redis-dev redis-cli --no-auth-warning -a "$REDIS_PASSWORD" ping 2>/dev/null | grep -q PONG; then
|
||
pass "Redis 响应 PONG"
|
||
else
|
||
warn "Redis ping 无响应（检查 REDIS_PASSWORD 或容器状态）"
|
||
fi
|
||
else
|
||
warn "docker/.env 缺 REDIS_PASSWORD，跳过 Redis 探活"
|
||
fi
|
||
|
||
# 5. 登录日志异常（24h 失败次数）
|
||
if [[ -n "${MYSQL_ROOT_PASSWORD:-}" ]] && docker inspect ys-mysql-dev >/dev/null 2>&1; then
|
||
FAILS=$(docker exec ys-mysql-dev sh -c \
|
||
"mysql -uroot -p\"\$MYSQL_ROOT_PASSWORD\" ${MYSQL_DATABASE:-payroll} -N -B -e \"
|
||
SELECT COUNT(*) FROM login_logs
|
||
WHERE success = 0 AND create_time > NOW() - INTERVAL 24 HOUR;\" 2>/dev/null" || echo "?")
|
||
if [[ "$FAILS" == "?" ]]; then
|
||
warn "登录日志查询失败"
|
||
elif (( FAILS < 10 )); then
|
||
pass "24h 登录失败 ${FAILS} 次（阈值 10）"
|
||
else
|
||
warn "24h 登录失败 ${FAILS} 次（可能有暴力破解，建议核查）"
|
||
fi
|
||
else
|
||
warn "跳过登录日志检查（无凭据或容器未运行）"
|
||
fi
|
||
|
||
echo "=============================================================="
|
||
if (( ISSUES == 0 )); then
|
||
echo "结论：全部通过，系统健康。"
|
||
exit 0
|
||
else
|
||
echo "结论：发现 $ISSUES 项需关注（见上）。"
|
||
exit 1
|
||
fi
|