mirror of
https://gitee.com/xmz7891/ykxmz.git
synced 2026-10-18 13:40:45 +00:00
修监测单元查错地址（改监听后它开始误报网站挂了）
把中转改成只监听 127.0.0.1（公网走 nginx）之后，监测单元还在查 http://13.54.30.196:13245/v1/health —— 那个端口已经不对公网开了， 于是它连续报"公网异常"，fails 涨到 2。 **差一点就是无限重启循环**：再失败一次它会启动紧急预案， 而预案的动作是"重启中转服务"，重启完再查还是 000，再救…… 这是改监听地址时没想到的连带影响。教训写在这里： **改一个服务的暴露方式时，必须把所有"探测它"的地方一起看一遍。** == 改法 == 监测地址改成"用户实际怎么访问"为准，域名优先、IP 兜底： PUBLIC_URL=http://yk.xxmxxs.top 域名（经 Cloudflare + nginx） FALLBACK_URL=http://13.54.30.196:80 绕过 CF 直连 nginx 只要有一个通就算健康。这样域名配好前靠兜底、配好后走真实路径。 == 顺带修的 == * monitor.log 属主还是 root（后来新建的），admin 写不进去 -> 再 chown 一次 * _build/check_lightsail.py 里的"公网"地址也要跟着改， 并且**故意保留**一项查 :13245（预期 000）用来确认 中转确实不再暴露公网 全量状态：三层地址、缓存头、监测、属主全部正确。
This commit is contained in:
xmz7891
+49
-38
@@ -1,14 +1,14 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
r'''看一眼 Lightsail 上中转服务器的完整状态。
|
||||
|
||||
为什么写成文件：用 `python -c @"..."@` 传带 `$(...)` 和引号的远端命令，
|
||||
PowerShell 会做变量插值、还会在本机执行 `$(systemctl ...)`
|
||||
（报 "无法将 systemctl 项识别为 cmdlet"）。凡是超过两行的远端命令，
|
||||
一律写成文件跑。
|
||||
⚠ 写这个文件的原因：用 `python -c @"..."@` 传带 `$(...)` 的远端命令，
|
||||
PowerShell 会**先在本机求值** `$(systemctl ...)`（报"无法将 systemctl
|
||||
项识别为 cmdlet"），还会吃掉引号导致 Python 语法错。
|
||||
这个毛病我这一轮犯了四五次 —— **凡是超过两行的远端命令，一律写文件。**
|
||||
|
||||
用法：
|
||||
python _build/check_lightsail.py
|
||||
python _build/check_lightsail.py --fix # 顺便修文件属主
|
||||
python _build/check_lightsail.py --fix # 顺便修文件属主
|
||||
'''
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -20,52 +20,63 @@ sys.path.insert(0, str(ROOT / "_build"))
|
||||
from lssh import run # noqa: E402
|
||||
|
||||
PORT = "13245"
|
||||
PUBLIC = "http://13.54.30.196:%s" % PORT
|
||||
DOMAIN = "yk.xxmxxs.top"
|
||||
RELAY_DIR = "/opt/ykxmz-relay"
|
||||
|
||||
# 三层地址各查一遍：
|
||||
# 域名 —— 用户实际走的路（Cloudflare -> nginx -> 中转）
|
||||
# IP:80 —— 绕过 Cloudflare，直连 nginx（域名没配好时靠它）
|
||||
# :13245 —— **应该不通**（中转已只绑 127.0.0.1，不再对公网）
|
||||
DOMAIN_URL = "http://%s" % DOMAIN
|
||||
NGINX_URL = "http://13.54.30.196:80"
|
||||
DIRECT_URL = "http://13.54.30.196:%s" % PORT
|
||||
|
||||
REMOTE = r'''
|
||||
R=__DIR__
|
||||
P=__PORT__
|
||||
|
||||
echo "════ 服务 ════"
|
||||
for s in ykxmz-relay ykxmz-monitor.timer; do
|
||||
printf ' %-24s %s\n' "$s" "$(systemctl is-active $s 2>&1)"
|
||||
for s in ykxmz-relay nginx ykxmz-monitor.timer; do
|
||||
printf ' %-22s %s\n' "$s" "$(systemctl is-active $s 2>&1)"
|
||||
done
|
||||
|
||||
echo
|
||||
echo "════ 健康 ════"
|
||||
printf ' %-24s %s\n' "本机 health" "$(curl -s -o /dev/null -w '%{http_code}' --max-time 8 http://127.0.0.1:$P/v1/health)"
|
||||
printf ' %-24s %s\n' "公网 health" "$(curl -s -o /dev/null -w '%{http_code}' --max-time 15 __PUBLIC__/v1/health)"
|
||||
printf ' %-24s %s\n' "公网首页" "$(curl -s -o /dev/null -w '%{http_code}' --max-time 15 __PUBLIC__/)"
|
||||
printf ' %-24s %s\n' "本机延迟" "$(curl -s -o /dev/null -w '%{time_total}s' --max-time 8 http://127.0.0.1:$P/v1/health)"
|
||||
printf ' %-24s %s\n' "公网延迟" "$(curl -s -o /dev/null -w '%{time_total}s' --max-time 15 __PUBLIC__/v1/health)"
|
||||
echo "════ 三层地址（用户路径 / 绕 CF / 直连中转）════"
|
||||
printf ' %-26s %s\n' "域名 __DOMAIN__" "$(curl -s -o /dev/null -w '%{http_code}' --max-time 12 __DOMAIN_URL__/v1/health)"
|
||||
printf ' %-26s %s\n' "IP:80（nginx）" "$(curl -s -o /dev/null -w '%{http_code}' --max-time 12 __NGINX_URL__/v1/health)"
|
||||
printf ' %-26s %s\n' ":__PORT__（应 000）" "$(curl -s -o /dev/null -w '%{http_code}' --max-time 8 __DIRECT_URL__/v1/health)"
|
||||
printf ' %-26s %s\n' "本机 :__PORT__" "$(curl -s -o /dev/null -w '%{http_code}' --max-time 8 http://127.0.0.1:$P/v1/health)"
|
||||
printf ' %-26s %s\n' "IP:80 延迟" "$(curl -s -o /dev/null -w '%{time_total}s' --max-time 12 __NGINX_URL__/v1/health)"
|
||||
|
||||
echo
|
||||
echo "════ 首页角标 ════"
|
||||
echo " 最新版: $(curl -s --max-time 10 http://127.0.0.1:$P/ | grep -o '最新版 [0-9.]*' | head -1)"
|
||||
echo " IP:80 -> $(curl -s --max-time 10 __NGINX_URL__/ | grep -o '最新版 [0-9.]*' | head -1)"
|
||||
echo " 域名 -> $(curl -s --max-time 12 __DOMAIN_URL__/ | grep -o '最新版 [0-9.]*' | head -1)"
|
||||
|
||||
echo
|
||||
echo "════ 缓存头（决定 Cloudflare 缓不缓存）════"
|
||||
printf ' %-20s %s 条\n' "下载" "$(curl -sI --max-time 10 __NGINX_URL__/download/ykxmz-setup-2.1.3.exe | grep -ci cache-control)"
|
||||
curl -sI --max-time 10 __NGINX_URL__/download/ykxmz-setup-2.1.3.exe \
|
||||
| grep -i '^cache-control' | sed 's/^/ /'
|
||||
printf ' %-20s %s\n' "长轮询" "$(curl -sI --max-time 10 __NGINX_URL__/v1/health | grep -i '^cache-control' | tr -d '\r')"
|
||||
|
||||
echo
|
||||
echo "════ 监听 / 进程 ════"
|
||||
ss -tlnp 2>/dev/null | grep ":$P " | sed 's/^/ /'
|
||||
ps -eo pid,rss,etime,cmd --sort=-rss 2>/dev/null | grep 'relay\.py' | grep -v grep | head -2 | sed 's/^/ /'
|
||||
ss -tlnp 2>/dev/null | grep -E ":(80|$P) " | sed 's/^/ /'
|
||||
ps -eo pid,rss,etime,cmd --sort=-rss 2>/dev/null | grep 'relay\.py' | grep -v grep | head -1 | sed 's/^/ /'
|
||||
|
||||
echo
|
||||
echo "════ 监测单元 ════"
|
||||
cat $R/monitor_state.txt 2>/dev/null | sed 's/^/ /'
|
||||
echo " --- monitor.log 尾部 ---"
|
||||
tail -4 $R/monitor.log 2>/dev/null | sed 's/^/ /'
|
||||
echo " --- 探测的是什么地址 ---"
|
||||
grep -E '^(PUBLIC_URL|FALLBACK_URL)=' $R/monitor.sh | sed 's/^/ /'
|
||||
echo " --- monitor.log 尾部（只挑非 Permission 的）---"
|
||||
grep -v 'Permission denied' $R/monitor.log 2>/dev/null | tail -4 | sed 's/^/ /'
|
||||
|
||||
echo
|
||||
echo "════ 抢救报告 ════"
|
||||
echo " 共 $(ls $R/rescue_reports 2>/dev/null | wc -l) 份"
|
||||
ls -la $R/rescue_reports/ 2>/dev/null | tail -n +4 | awk '{print " " $6" "$7" "$8" "$9}'
|
||||
|
||||
echo
|
||||
echo "════ 知识库 ════"
|
||||
if [ -f $R/rescue_knowledge.md ]; then
|
||||
echo " $(wc -l < $R/rescue_knowledge.md) 行"
|
||||
else
|
||||
echo " （还没有）"
|
||||
fi
|
||||
echo "════ 抢救报告 / 知识库 ════"
|
||||
echo " 报告 $(ls $R/rescue_reports 2>/dev/null | wc -l) 份"
|
||||
echo " 知识库 $(wc -l < $R/rescue_knowledge.md 2>/dev/null || echo 0) 行"
|
||||
|
||||
echo
|
||||
echo "════ 资源 ════"
|
||||
@@ -74,11 +85,7 @@ df -h / | tail -1 | awk '{printf " 磁盘 %s 用 %s\n", $2, $5}'
|
||||
uptime | sed 's/^/ /'
|
||||
|
||||
echo
|
||||
echo "════ 定时器下次触发 ════"
|
||||
systemctl list-timers ykxmz-monitor.timer --no-pager 2>/dev/null | head -3 | sed 's/^/ /'
|
||||
|
||||
echo
|
||||
echo "════ 文件属主（admin 要能写日志）════"
|
||||
echo "════ 文件属主（admin 必须能写日志）════"
|
||||
ls -la $R/*.log $R/monitor_state.txt 2>/dev/null | awk '{print " " $3":"$4" "$9}'
|
||||
'''
|
||||
|
||||
@@ -87,12 +94,16 @@ def main() -> int:
|
||||
if "--fix" in sys.argv:
|
||||
print(" ── 修属主 ──")
|
||||
out = run("sudo chown -R admin:admin %s && sudo chmod 755 %s && echo OK"
|
||||
% (RELAY_DIR, RELAY_DIR), timeout=120)
|
||||
% (RELAY_DIR, RELAY_DIR), timeout=120, quiet=True)
|
||||
print(" " + out[1].strip())
|
||||
|
||||
cmd = (REMOTE.replace("__DIR__", RELAY_DIR)
|
||||
cmd = (REMOTE
|
||||
.replace("__DIR__", RELAY_DIR)
|
||||
.replace("__PORT__", PORT)
|
||||
.replace("__PUBLIC__", PUBLIC))
|
||||
.replace("__DOMAIN__", DOMAIN)
|
||||
.replace("__DOMAIN_URL__", DOMAIN_URL)
|
||||
.replace("__NGINX_URL__", NGINX_URL)
|
||||
.replace("__DIRECT_URL__", DIRECT_URL))
|
||||
out = run(cmd, timeout=300, quiet=True)
|
||||
print(out[1] if isinstance(out, tuple) else out)
|
||||
return 0
|
||||
|
||||
Reference in New Issue
Block a user