first

domain-api/app/services/worker_control_service.py

@@ -3,12 +3,18 @@ from __future__ import annotations
 import json
 import os
 import subprocess
+from datetime import datetime
 from pathlib import Path
 
 from app.core.config import settings
+from app.core.redis_client import get_redis
 from app.services.runtime_settings_service import get_runtime_settings
 
 
+WORKER_CONTROL_CHANNEL = "domain_tool:worker_control"
+WORKER_PENDING_COMMAND_KEY = "domain_tool:worker_pending_command"
+
+
 def _domain_root() -> Path:
     return Path(settings.domain_root)
 
@@ -30,6 +36,73 @@ def _run_shell(command: list[str], timeout: int = 20) -> subprocess.CompletedPro
     return subprocess.run(command, capture_output=True, text=True, timeout=timeout)
 
 
+def _run_systemctl(command: list[str], timeout: int = 20, require_sudo: bool = True) -> subprocess.CompletedProcess[str]:
+    systemctl_command = ["systemctl", *command]
+    if os.geteuid() == 0 or not require_sudo:
+        return _run_shell(systemctl_command, timeout=timeout)
+    return _run_shell(["sudo", "-n", *systemctl_command], timeout=timeout)
+
+
+def _parse_systemd_timestamp(raw_timestamp: str) -> str:
+    raw_timestamp = (raw_timestamp or "").strip()
+    if not raw_timestamp:
+        return ""
+    try:
+        parsed = datetime.strptime(raw_timestamp, "%a %Y-%m-%d %H:%M:%S %Z")
+        return parsed.strftime("%Y-%m-%d %H:%M:%S")
+    except ValueError:
+        pass
+    try:
+        parsed = datetime.strptime(raw_timestamp.rsplit(" ", 1)[0], "%a %Y-%m-%d %H:%M:%S")
+        return parsed.strftime("%Y-%m-%d %H:%M:%S")
+    except ValueError:
+        return ""
+
+
+def probe_systemd_service(service_name: str, *, mode: str = "linux-systemd") -> dict:
+    result = _run_systemctl(
+        [
+            "show",
+            service_name,
+            "--no-page",
+            "--property=ActiveState,SubState,MainPID,ExecMainStartTimestamp,ActiveEnterTimestamp",
+        ],
+        require_sudo=False,
+    )
+    output = (result.stdout or result.stderr or "").strip()
+    if result.returncode != 0:
+        return {
+            "mode": mode,
+            "service_name": service_name,
+            "running": False,
+            "process_count": 0,
+            "latest_start_time": "",
+            "message": output or f"systemd service {service_name} not available",
+        }
+
+    data: dict[str, str] = {}
+    for line in output.splitlines():
+        if "=" in line:
+            key, value = line.split("=", 1)
+            data[key] = value
+    main_pid = int(data.get("MainPID", "0") or 0)
+    active_state = data.get("ActiveState", "")
+    sub_state = data.get("SubState", "")
+    latest_start_time = ""
+    for raw_timestamp in (data.get("ExecMainStartTimestamp", ""), data.get("ActiveEnterTimestamp", "")):
+        latest_start_time = _parse_systemd_timestamp(raw_timestamp)
+        if latest_start_time:
+            break
+    return {
+        "mode": mode,
+        "service_name": service_name,
+        "running": active_state == "active",
+        "process_count": 1 if main_pid > 0 else 0,
+        "latest_start_time": latest_start_time,
+        "message": f"{active_state}/{sub_state}" if active_state else "",
+    }
+
+
 def _windows_runtime() -> dict:
     command = """
     $targets = Get-CimInstance Win32_Process -Filter "name='python.exe'" |
@@ -83,32 +156,23 @@ def _windows_runtime() -> dict:
 def _linux_runtime() -> dict:
     runtime = _runtime_config()
     service_name = runtime["worker_service_name"]
-    result = _run_shell(["systemctl", "show", service_name, "--no-page", "--property=ActiveState,SubState,MainPID"])
-    output = (result.stdout or result.stderr or "").strip()
-    if result.returncode != 0:
+    return probe_systemd_service(service_name, mode="linux-systemd")
+
+
+def detect_sync_agent_runtime() -> dict:
+    runtime = _runtime_config()
+    worker_mode = runtime.get("worker_mode", settings.worker_mode)
+    service_name = runtime.get("sync_agent_service_name", settings.sync_agent_service_name)
+    if worker_mode != "linux-systemd":
         return {
-            "mode": "linux-systemd",
+            "mode": worker_mode,
+            "service_name": service_name,
             "running": False,
             "process_count": 0,
             "latest_start_time": "",
-            "message": output or f"systemd service {service_name} not available",
+            "message": "sync-agent 仅在 Linux systemd 多机部署中使用",
         }
-
-    data: dict[str, str] = {}
-    for line in output.splitlines():
-        if "=" in line:
-            key, value = line.split("=", 1)
-            data[key] = value
-    main_pid = int(data.get("MainPID", "0") or 0)
-    active_state = data.get("ActiveState", "")
-    sub_state = data.get("SubState", "")
-    return {
-        "mode": "linux-systemd",
-        "running": active_state == "active",
-        "process_count": 1 if main_pid > 0 else 0,
-        "latest_start_time": "",
-        "message": f"{active_state}/{sub_state}" if active_state else "",
-    }
+    return probe_systemd_service(service_name, mode="linux-systemd")
 
 
 def detect_worker_runtime() -> dict:
@@ -132,7 +196,7 @@ def start_worker() -> tuple[bool, str]:
     worker_mode = runtime["worker_mode"]
     service_name = runtime["worker_service_name"]
     if worker_mode == "linux-systemd":
-        result = _run_shell(["systemctl", "start", service_name], timeout=30)
+        result = _run_systemctl(["start", service_name], timeout=30)
         if result.returncode != 0:
             return False, (result.stderr or result.stdout or "启动 Linux Worker 失败").strip()
         return True, f"Linux Worker 启动命令已发送: {service_name}"
@@ -160,7 +224,7 @@ def stop_worker() -> tuple[bool, str]:
     worker_mode = runtime["worker_mode"]
     service_name = runtime["worker_service_name"]
     if worker_mode == "linux-systemd":
-        result = _run_shell(["systemctl", "stop", service_name], timeout=30)
+        result = _run_systemctl(["stop", service_name], timeout=30)
         if result.returncode != 0:
             return False, (result.stderr or result.stdout or "停止 Linux Worker 失败").strip()
         return True, f"Linux Worker 停止命令已发送: {service_name}"
@@ -186,3 +250,17 @@ def stop_worker() -> tuple[bool, str]:
     if "NO_PROCESS" in output:
         return True, "当前没有运行中的检测端进程"
     return True, output or "检测端已停止"
+
+
+def send_worker_command(action: str, payload: dict | None = None) -> tuple[bool, str]:
+    try:
+        redis_client = get_redis()
+        command_payload = {"action": action}
+        if payload:
+            command_payload.update(payload)
+        serialized = json.dumps(command_payload, ensure_ascii=False)
+        redis_client.set(WORKER_PENDING_COMMAND_KEY, serialized, ex=120)
+        redis_client.publish(WORKER_CONTROL_CHANNEL, serialized)
+        return True, f"已发送 Worker 控制指令: {action}"
+    except Exception as exc:
+        return False, f"发送 Worker 控制指令失败: {exc}"