feat(health): /health 深检——磁盘水位 + 下游依赖 TCP 探测，异常返回 503 degraded

背景: 9·19 磁盘满事故中业务已瘫但 /health 仍 200（只看模型就绪标志），网关持续把流量打到本机。深检让 worker 在磁盘不足(min_free_gb, 默认5G)或 ComfyUI/change_hair TCP 不通时主动报 503，网关探测两次失败即摘除。 - 配置: worker_config.json "health" 段，env HEALTH_MIN_FREE_GB/ HEALTH_CHECK_DEPS/HEALTH_DEP_COMFYUI/HEALTH_DEPS_CACHE_SECONDS 可覆盖 - 依赖探测 0.8s 超时并发执行，结果缓存 5s；深检自身异常按就绪返回 - 测试: 深检各分支用例 + 旧用例改为 mock 深检（不依赖本机服务）
2026-09-20 21:46:18 +08:00
parent 3f8d90d963
commit 14562d4869
3 changed files with 196 additions and 6 deletions
@@ -2,15 +2,20 @@

 接口 1（四庭七眼测量）已为**真实算法实现**（见 face_analysis 包）；接口 2~5 仍为 Mock。
 拆分架构：worker 跑算法、返回 `annotated_image_base64`（不落盘、不拼 URL，由网关完成）。
-worker 对 `/api/*` 校验内网鉴权头 `X-Internal-Token`，`/health` 供网关探测不校验。
+worker 对 `/api/*` 校验内网鉴权头 `X-Internal-Token`，`/health` 供网关探测不校验
+（深检：磁盘水位 + 下游依赖 TCP 探测，异常返回 503 degraded，见 _load_health_cfg）。
 """
+import asyncio
 import base64
 import json
 import logging
 import os
+import shutil
+import time
 from contextlib import asynccontextmanager
 from io import BytesIO
 from typing import Any, List, Optional
+from urllib.parse import urlsplit

 import cv2
 import numpy as np
@@ -1911,12 +1916,127 @@ async def download_hairline_log(rid: Optional[str] = None, tail: int = 500):
 # 健康检查
 # ---------------------------------------------------------------------------

+def _load_health_cfg() -> dict:
+    """深健康检查配置：环境变量优先，回退 worker_config.json 的 "health" 段。
+
+    min_free_gb=0 关闭磁盘检查；check_deps=false 关闭依赖探测（均退化为旧行为，
+    即只看模型就绪标志）。
+    """
+    cfg_path = os.path.join(os.path.dirname(__file__), "worker_config.json")
+    file_cfg: dict = {}
+    if os.path.isfile(cfg_path):
+        try:
+            with open(cfg_path, encoding="utf-8") as f:
+                file_cfg = json.load(f).get("health") or {}
+        except Exception as e:  # noqa: BLE001
+            logger.warning("读取 worker_config.json health 段失败：%s", e)
+
+    def _get(env_key, file_key, default):
+        raw = os.getenv(env_key)
+        return raw if raw not in (None, "") else file_cfg.get(file_key, default)
+
+    def _as_float(value, default):
+        try:
+            return float(value)
+        except (TypeError, ValueError):
+            return default
+
+    return {
+        "min_free_gb": _as_float(_get("HEALTH_MIN_FREE_GB", "min_free_gb", 5.0), 5.0),
+        "check_deps": str(_get("HEALTH_CHECK_DEPS", "check_deps", True)).strip().lower()
+                      not in ("0", "false", "no", "off"),
+        "dep_comfyui": str(_get("HEALTH_DEP_COMFYUI", "dep_comfyui", "127.0.0.1:8188")),
+        "deps_cache_seconds": max(0.0, _as_float(
+            _get("HEALTH_DEPS_CACHE_SECONDS", "deps_cache_seconds", 5.0), 5.0)),
+    }
+
+
+_HEALTH_CFG = _load_health_cfg()
+
+
+def _disk_free_gb() -> float:
+    """worker 所在文件系统的剩余空间（GB）。"""
+    st = shutil.disk_usage(os.path.dirname(os.path.abspath(__file__)))
+    return st.free / (1 << 30)
+
+
+def _parse_host_port(addr: str, default_port: int):
+    """解析 "host:port"（仅支持 IPv4/主机名形式）。"""
+    host, _, port = str(addr).partition(":")
+    try:
+        return host or "127.0.0.1", int(port) if port else default_port
+    except ValueError:
+        return host or "127.0.0.1", default_port
+
+
+def _change_hair_addr():
+    """从 _CHANGE_HAIR_BASE 解析 (host, port)，失败返回 None。"""
+    try:
+        u = urlsplit(_CHANGE_HAIR_BASE)
+        if u.hostname:
+            return u.hostname, u.port or 80
+    except ValueError:
+        pass
+    return None
+
+
+async def _tcp_probe(host: str, port: int, timeout: float = 0.8) -> bool:
+    """TCP 连通性探测：只判下游进程死活，不过 HTTP 认证、不受业务繁忙影响。"""
+    try:
+        _, writer = await asyncio.wait_for(asyncio.open_connection(host, port), timeout)
+        writer.close()
+        return True
+    except Exception:  # noqa: BLE001
+        return False
+
+
+_DEP_CACHE = {"ts": -1.0, "detail": None}
+
+
+async def _check_deps():
+    """并发探测下游依赖（ComfyUI、change_hair），结果缓存 deps_cache_seconds 秒。"""
+    now = time.monotonic()
+    detail = _DEP_CACHE["detail"]
+    if detail is None or now - _DEP_CACHE["ts"] >= _HEALTH_CFG["deps_cache_seconds"]:
+        probes = {"comfyui": _tcp_probe(*_parse_host_port(_HEALTH_CFG["dep_comfyui"], 8188))}
+        ch = _change_hair_addr()
+        if ch:
+            probes["change_hair"] = _tcp_probe(*ch)
+        names = list(probes)
+        results = await asyncio.gather(*probes.values())
+        detail = dict(zip(names, results))
+        _DEP_CACHE["ts"], _DEP_CACHE["detail"] = now, detail
+    return all(detail.values()), detail
+
+
@app.get("/health", include_in_schema=False)
 async def health():
-    # 模型就绪后才返回 200，供网关探测；未就绪返回 503。
+    """网关探测入口。
+
+    模型未就绪 → 503 starting；磁盘剩余低于阈值 / 下游依赖 TCP 不通 → 503 degraded；
+    正常 → 200（附 disk_free_gb 与 deps 明细，供人工排查）。深检自身异常时按就绪返回
+    （健康检查不能自己成为故障点）。
+    """
    if not _STATE["ready"]:
        return JSONResponse(status_code=503, content={"status": "starting"})
-    return {"status": "ok"}
+    try:
+        free_gb = _disk_free_gb()
+        body = {"status": "ok", "disk_free_gb": round(free_gb, 1)}
+        min_free = _HEALTH_CFG["min_free_gb"]
+        if min_free > 0 and free_gb < min_free:
+            body.update(status="degraded", reason=f"disk_free_below_{min_free}g")
+            return JSONResponse(status_code=503, content=body)
+        if _HEALTH_CFG["check_deps"]:
+            deps_ok, detail = await _check_deps()
+            body["deps"] = detail
+            if not deps_ok:
+                down = ",".join(k for k, v in detail.items() if not v)
+                body.update(status="degraded", reason=f"dep_down:{down}")
+                return JSONResponse(status_code=503, content=body)
+        return body
+    except Exception:  # noqa: BLE001
+        logger.exception("深健康检查异常，按就绪返回")
+        return {"status": "ok"}


@app.get("/", include_in_schema=False)
@@ -36,12 +36,76 @@ def test_auth_missing_token_401(client):
    assert r.status_code == 401


-def test_health_no_token_200(client):
+def _patch_health_ok(monkeypatch):
+    """让 /health 深检确定性通过：不依赖本机磁盘水位与 8188/8801 服务存活。"""
+    monkeypatch.setattr(app_module, "_HEALTH_CFG", {
+        **app_module._HEALTH_CFG, "min_free_gb": 0.0, "check_deps": True})
+
+    async def _deps_ok():
+        return True, {"comfyui": True, "change_hair": True}
+    monkeypatch.setattr(app_module, "_check_deps", _deps_ok)
+
+
+def test_health_no_token_200(client, monkeypatch):
+    _patch_health_ok(monkeypatch)
    r = client.get("/health")
    assert r.status_code == 200
    assert r.json()["status"] == "ok"


+def test_health_disk_low_503(client, monkeypatch):
+    # 阈值调到不可能的 99999G → 必然触发磁盘水位 503
+    monkeypatch.setattr(app_module, "_HEALTH_CFG", {
+        **app_module._HEALTH_CFG, "min_free_gb": 99999.0, "check_deps": False})
+    r = client.get("/health")
+    assert r.status_code == 503
+    body = r.json()
+    assert body["status"] == "degraded"
+    assert body["reason"].startswith("disk_free_below")
+
+
+def test_health_dep_down_503(client, monkeypatch):
+    monkeypatch.setattr(app_module, "_HEALTH_CFG", {
+        **app_module._HEALTH_CFG, "min_free_gb": 0.0, "check_deps": True})
+
+    async def _deps_down():
+        return False, {"comfyui": False, "change_hair": True}
+    monkeypatch.setattr(app_module, "_check_deps", _deps_down)
+    r = client.get("/health")
+    assert r.status_code == 503
+    body = r.json()
+    assert body["status"] == "degraded"
+    assert "comfyui" in body["reason"]
+
+
+def test_health_ok_carries_detail(client, monkeypatch):
+    _patch_health_ok(monkeypatch)
+    r = client.get("/health")
+    assert r.status_code == 200
+    body = r.json()
+    assert "disk_free_gb" in body
+    assert body["deps"] == {"comfyui": True, "change_hair": True}
+
+
+def test_tcp_probe_real_socket():
+    # 用进程内真实 socket 验证探测本身（曾因 open_connection 返回元组误判全部不可达）
+    import asyncio
+
+    async def scenario():
+        server = await asyncio.start_server(lambda r, w: None, host="127.0.0.1", port=0)
+        port = server.sockets[0].getsockname()[1]
+        up = await app_module._tcp_probe("127.0.0.1", port)
+        server.close()
+        await server.wait_closed()
+        # 端口 1 无监听，本机 connect 立即被拒
+        down = await app_module._tcp_probe("127.0.0.1", 1)
+        return up, down
+
+    up, down = asyncio.run(scenario())
+    assert up is True
+    assert down is False
+
+
 def test_param_none_provided_1007(client):
    r = client.post(URL, headers=H)
    assert r.json()["code"] == 1007
@@ -1,5 +1,11 @@
 {
-  "_comment": "复制为 worker_config.json（不入 git）。accept_passwords：worker 内网鉴权密码列表，网关带 X-Internal-Token: <其中之一>（也可用环境变量 WORKER_ACCEPT_PASSWORDS 覆盖）。comfyui_password：本机 ComfyUI(8188) Basic Auth 密码（user 默认 admin；也可放 password.txt 或环境变量 COMFYUI_PASSWORD）。注：接口4 火山方舟 ark_api_key 已迁到网关配置。",
+  "_comment": "复制为 worker_config.json（不入 git）。accept_passwords：worker 内网鉴权密码列表，网关带 X-Internal-Token: <其中之一>（也可用环境变量 WORKER_ACCEPT_PASSWORDS 覆盖）。comfyui_password：本机 ComfyUI(8188) Basic Auth 密码（user 默认 admin；也可放 password.txt 或环境变量 COMFYUI_PASSWORD）。health：深健康检查（/health 磁盘水位+下游依赖 TCP 探测，均可用环境变量 HEALTH_MIN_FREE_GB / HEALTH_CHECK_DEPS / HEALTH_DEP_COMFYUI / HEALTH_DEPS_CACHE_SECONDS 覆盖）。注：接口4 火山方舟 ark_api_key 已迁到网关配置。",
  "accept_passwords": ["change-me-to-a-strong-secret"],
-  "comfyui_password": "your-comfyui-basic-auth-password"
+  "comfyui_password": "your-comfyui-basic-auth-password",
+  "health": {
+    "min_free_gb": 5,
+    "check_deps": true,
+    "dep_comfyui": "127.0.0.1:8188",
+    "deps_cache_seconds": 5
+  }
 }