lianlonggangandClaude
68751c2354
- WebSocket 连接 B 端（注册/心跳/指数退避重连） - 命令分发（10 种远程运维命令） - 看门狗守护、日志实时流、在线升级含自动回滚 - 修复 main.py 日志格式 style 与占位符不匹配的问题 - 补充 README、配置示例、依赖清单 Co-Authored-By: Claude <noreply@anthropic.com>
111 lines
3.8 KiB
Python
111 lines
3.8 KiB
Python
# -*- coding: utf-8 -*-
|
||
"""主程序进程守护（看门狗）。
|
||
|
||
周期探测主程序健康：
|
||
- 连续 3 次失败 → 认为主程序宕机 → 强杀残留 → 调启动命令拉起
|
||
- 拉起后等待健康恢复；连续 3 次拉起失败 → 上报告警（ALERT）
|
||
"""
|
||
|
||
import logging
|
||
import subprocess
|
||
import threading
|
||
|
||
log = logging.getLogger(__name__)
|
||
|
||
|
||
class ProcessGuard:
|
||
"""看门狗：周期健康探测 + 宕机拉起 + 告警上报。"""
|
||
|
||
def __init__(self, config, main_app_client, client):
|
||
self.config = config
|
||
self.main_app_client = main_app_client
|
||
self.client = client
|
||
|
||
self._fail_count = 0 # 连续健康探测失败次数
|
||
self._restart_count = 0 # 连续拉起次数
|
||
self._stop = threading.Event()
|
||
self._thread: threading.Thread | None = None
|
||
|
||
def start(self):
|
||
"""启动守护（首检延迟 30 秒，之后每 15 秒探测一次）。"""
|
||
if not self.config.guard_enabled:
|
||
log.info("进程守护未启用（guard.enable=false）")
|
||
return
|
||
self._thread = threading.Thread(target=self._loop, name="process-guard", daemon=True)
|
||
self._thread.start()
|
||
log.info("进程守护已启动：每 15 秒探测 %s", self.config.main_health_url)
|
||
|
||
def stop(self):
|
||
"""停止守护。"""
|
||
self._stop.set()
|
||
|
||
# ================= 探测循环 =================
|
||
|
||
def _loop(self):
|
||
"""探测主循环：先等 30 秒（给主程序启动时间），再周期探测。"""
|
||
if self._stop.wait(30):
|
||
return
|
||
while not self._stop.wait(15):
|
||
try:
|
||
self._check()
|
||
except Exception as e:
|
||
log.warning("守护探测异常：%s", e)
|
||
|
||
def _check(self):
|
||
"""单次探测：健康则清零计数；连续 3 次失败则拉起。"""
|
||
health = self.main_app_client.health()
|
||
if health.get("ok") is True:
|
||
self._fail_count = 0
|
||
return
|
||
|
||
self._fail_count += 1
|
||
log.warning("主程序健康探测失败（%d/3）：%s", self._fail_count, health.get("error"))
|
||
if self._fail_count < 3:
|
||
return
|
||
|
||
# 连续 3 次失败 → 拉起
|
||
self._fail_count = 0
|
||
self._restart_count += 1
|
||
attempts = self._restart_count
|
||
if attempts > 3:
|
||
self.client.send("ALERT", {
|
||
"level": "CRITICAL",
|
||
"msg": f"主程序连续 {attempts} 次拉起失败，请人工介入",
|
||
})
|
||
# 重置计数，之后继续尝试（降频可后续优化）
|
||
self._restart_count = 3
|
||
return
|
||
|
||
log.error("主程序宕机，执行第 %d 次拉起：%s", attempts, self.config.main_start_cmd)
|
||
self.client.send("ALERT", {
|
||
"level": "WARN",
|
||
"msg": f"主程序宕机，Agent 正在执行第 {attempts} 次拉起",
|
||
})
|
||
try:
|
||
proc = start_main_app(self.config.main_start_cmd)
|
||
log.info("启动命令已执行，pid=%s", proc.pid if proc else None)
|
||
except Exception as e:
|
||
log.error("启动命令执行失败：%s", e)
|
||
|
||
|
||
# ================= 公共工具（upgrade.py 复用） =================
|
||
|
||
def start_main_app(start_cmd: str) -> subprocess.Popen | None:
|
||
"""
|
||
拉起主程序。
|
||
|
||
Windows 下 .bat 走 cmd /c（路径转反斜杠）；其余走 sh。
|
||
返回 Popen 对象（不等待进程结束）。
|
||
"""
|
||
cmd = start_cmd.replace("/", "\\") # cmd/c 要求反斜杠路径
|
||
if cmd.lower().endswith(".bat"):
|
||
args = ["cmd", "/c", cmd, "start"]
|
||
else:
|
||
args = ["sh", start_cmd, "start"]
|
||
return subprocess.Popen(
|
||
args,
|
||
stdout=subprocess.DEVNULL,
|
||
stderr=subprocess.STDOUT,
|
||
# 不设 cwd，继承 Agent 工作目录（与主程序同根目录部署）
|
||
)
|