feat(gateway): 全局串行化(并发=1) + 记录入参/出参/耗时日志

并发模型从「每worker并发1 + 多worker并行」改为全局串行：同一时间只处理1个请求，其余排队；多 worker 仅作热备（主 worker 坏了才用备机）。接口4(face/features) 走豆包、不占 GPU，不纳入串行。 - pool: asyncio.Semaphore(max_global_concurrency=1) + acquire/release_global_slot （依赖单进程 uvicorn 部署，已在注释中标注） - forward: proxy_request 最外层 acquire 全局槽、try/finally 全路径释放；入参 multipart 解析挂 request.state；原重试/故障转移逻辑抽到 _dispatch_with_retries - reqlog(新): 标量入参保留；图片(file/base64)存盘转URL，绝不内嵌base64；出参递归摘要截断(landmarks/长串/大数组) - logging_middleware: RequestLogEntry 加 request_params/response_data， jsonl 全量记录；_load_from_logfile 同步映射防重启丢字段；get_stats recent 暴露 - /gateway-health 暴露 global_max/global_busy/global_waiting - config: dispatch 新增 max_global_concurrency / max_queue_wait_seconds - tests: test_reqlog + test_gateway_serialization（9 用例）顺带提交此前未提交的网关统计(daily stats 接口)与耗时看板(api_timing_dashboard.html)。 Co-Authored-By: Claude <noreply@anthropic.com>
2026-07-23 22:56:48 +08:00
parent 98b9108837
commit bb9f55e93c
10 changed files with 1037 additions and 7 deletions
@@ -0,0 +1,58 @@
+"""gateway.pool 全局串行槽单测：验证 max_global_concurrency=1 时同一时间只跑1个请求、
+排队超时返回 False。
+
+用 asyncio.run 套同步测试，避免引入 pytest-asyncio 依赖。
+"""
+
+import asyncio
+
+from gateway import pool
+
+_CFG = {"dispatch": {"max_global_concurrency": 1, "max_queue_wait_seconds": 590}}
+_CFG_FAST_TIMEOUT = {"dispatch": {"max_global_concurrency": 1, "max_queue_wait_seconds": 0.2}}
+
+
+def test_global_slot_serializes_to_one():
+    pool.init_global_slot(_CFG)
+
+    state = {"active": 0, "peak": 0}
+
+    async def task():
+        got = await pool.acquire_global_slot(_CFG)
+        assert got is True
+        state["active"] += 1
+        state["peak"] = max(state["peak"], state["active"])
+        await asyncio.sleep(0.03)
+        state["active"] -= 1
+        pool.release_global_slot()
+
+    async def run():
+        await asyncio.gather(*(task() for _ in range(4)))
+
+    asyncio.run(run())
+    assert state["peak"] == 1, f"期望峰值并发=1，实际={state['peak']}"
+    assert pool.get_pool_status()["global_busy"] == 0
+
+
+def test_global_slot_timeout_returns_false():
+    pool.init_global_slot(_CFG_FAST_TIMEOUT)
+
+    async def run():
+        first = await pool.acquire_global_slot(_CFG_FAST_TIMEOUT)
+        assert first is True
+        # 槽已被占用，第二个应在 0.2s 内超时
+        second = await pool.acquire_global_slot(_CFG_FAST_TIMEOUT)
+        assert second is False
+        pool.release_global_slot()
+
+    asyncio.run(run())
+    assert pool.get_pool_status()["global_busy"] == 0
+
+
+def test_get_pool_status_has_global_fields():
+    pool.init_global_slot(_CFG)
+    status = pool.get_pool_status()
+    assert "global_max" in status
+    assert "global_busy" in status
+    assert "global_waiting" in status
+    assert status["global_max"] == 1
@@ -0,0 +1,109 @@
+"""gateway.reqlog 单测：multipart 入参解析（标量 + 图片存盘转 URL）+ 出参摘要。
+
+不依赖网络 / GPU，纯函数级。
+"""
+
+import base64
+import json
+
+from gateway.reqlog import extract_form_params, summarize_for_log
+
+# 1x1 透明 PNG（合法 magic byte）
+_PNG = (
+    b"\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x01\x00\x00\x00\x01"
+    b"\x08\x06\x00\x00\x00\x1f\x15\xc4\x89\x00\x00\x00\nIDATx\x9cc\x00\x01"
+    b"\x00\x00\x05\x00\x01\r\n-\xb4\x00\x00\x00\x00IEND\xaeB`\x82"
+)
+
+
+def _multipart(fields, files, boundary=b"----testbnd"):
+    """手搓 multipart/form-data body。fields: {name:str}; files: {name:(fname,ctype,bytes)}."""
+    parts = []
+    for name, val in fields.items():
+        parts.append(b"--" + boundary + b"\r\n")
+        parts.append(b'Content-Disposition: form-data; name="' + name.encode() + b'"\r\n\r\n')
+        parts.append(val.encode("utf-8") + b"\r\n")
+    for name, (fname, ctype, data) in files.items():
+        parts.append(b"--" + boundary + b"\r\n")
+        parts.append(b'Content-Disposition: form-data; name="' + name.encode() + b'"; filename="'
+                     + fname.encode() + b'"\r\n')
+        parts.append(b"Content-Type: " + ctype.encode() + b"\r\n\r\n")
+        parts.append(data + b"\r\n")
+    parts.append(b"--" + boundary + b"--\r\n")
+    return b"".join(parts)
+
+
+def test_extract_scalars_and_images(tmp_path):
+    b64 = "data:image/png;base64," + base64.b64encode(_PNG).decode()
+    body = _multipart(
+        fields={"gender": "female", "hair_style": "1,3", "use_mask": "True",
+                "prompt": "填充遮罩区域的头发", "image_base64": b64},
+        files={"image_file": ("x.png", "image/png", _PNG)},
+    )
+    ct = "multipart/form-data; boundary=----testbnd"
+
+    res = extract_form_params(ct, body, str(tmp_path), "https://test.local")
+
+    # 标量原样
+    assert res["gender"] == "female"
+    assert res["hair_style"] == "1,3"
+    assert res["use_mask"] == "True"
+
+    # 图片字段是元信息 dict（不是 base64 文本）
+    assert res["image_file"]["_image"] is True
+    assert res["image_file"]["source"] == "file"
+    assert res["image_file"]["filename"] == "x.png"
+    assert res["image_file"]["url"] is not None
+    assert res["image_base64"]["_image"] is True
+    assert res["image_base64"]["source"] == "base64"
+    assert res["image_base64"]["url"] is not None
+
+    # 图片已落盘
+    saved = [p.name for p in tmp_path.iterdir()]
+    assert any(n.startswith("in_") and n.endswith(".png") for n in saved)
+    # URL 指向正确路径
+    assert res["image_file"]["url"].startswith("https://test.local/static/annotations/in_")
+
+    # 关键：日志里绝不包含 base64 文本
+    blob = json.dumps(res, ensure_ascii=False)
+    assert b64.split(",", 1)[1][:40] not in blob
+
+
+def test_extract_non_multipart(tmp_path):
+    res = extract_form_params("application/json", b'{"a":1}', str(tmp_path), "https://t.local")
+    assert res == {"_content_type": "application/json", "_body_bytes": 7}
+
+
+def test_extract_empty_content_type(tmp_path):
+    res = extract_form_params("", b"hello", str(tmp_path), "https://t.local")
+    assert res["_body_bytes"] == 5
+
+
+def test_summarize_truncates_long_values():
+    big = {
+        "landmarks": [[i, i] for i in range(500)],
+        "name": "x" * 1000,
+        "deep": {"a": {"b": {"c": {"d": {"e": {"f": {"g": 1}}}}}}},
+    }
+    sm = summarize_for_log(big)
+    # 长数组被截断 + 标注剩余数
+    assert isinstance(sm["landmarks"], list)
+    assert sm["landmarks"][-1].startswith("…(+")
+    assert len(sm["landmarks"]) == 6  # 5 项 + 1 个标注
+    # 长字符串被截断
+    assert "…(+" in sm["name"]
+    # 总体积受控
+    assert len(json.dumps(sm, ensure_ascii=False).encode()) <= 8192
+
+
+def test_summarize_keeps_small_intact():
+    obj = {"code": 0, "data": {"hairline_images": [{"order": 1, "image_middle_url": "https://x/y.png"}]}}
+    assert summarize_for_log(obj) == obj
+
+
+def test_summarize_byte_cap_stub():
+    # 构造大量小字段触发字节上限
+    obj = {f"k{i}": {f"j{j}": "abcdefghij" for j in range(50)} for i in range(50)}
+    sm = summarize_for_log(obj, max_bytes=2048)
+    assert isinstance(sm, dict) and sm.get("_truncated") is True
+    assert "size_bytes" in sm