feat: 完成 issue #61 ⑥ 可用性监控探针（≥99.8%）

2026-08-05 03:19:19 +08:00
parent c8d6e725a2
commit f6cdc84860
3 changed files with 312 additions and 0 deletions
@@ -0,0 +1,104 @@
+# -*- coding: utf-8 -*-
+"""可用性监控探针测试（issue #61）。
+
+用本地 ThreadingHTTPServer 模拟健康端点：
+1. 稳定 200 → 可用率 100% ≥ 99.8%；
+2. 间歇 503 → 可用率按失败比例下降，探针统计正确；
+3. 阈值判断：间歇失败超 0.2% 时 meets_target=False；
+4. 失败明细记录（URL + 原因）。
+"""
+import http.server
+import os
+import sys
+import threading
+import unittest
+
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+from probe_availability import AvailabilityProbe  # noqa: E402
+
+
+class _HealthHandler(http.server.BaseHTTPRequestHandler):
+    """可配置成功/失败模式的 /health 处理器。"""
+
+    fail_mode = []  # [True/False...] 按请求序号循环
+
+    def do_GET(self):
+        if self.path == "/health":
+            if self.fail_mode and self.fail_mode[0]:
+                self.fail_mode[0] = False  # 一次性失败
+                self.send_response(503)
+            else:
+                self.send_response(200)
+        else:
+            self.send_response(404)
+        self.end_headers()
+
+    def log_message(self, *args):  # 静默日志
+        pass
+
+
+def start_server(fail_once=False):
+    handler = _HealthHandler
+    handler.fail_mode = [True] if fail_once else []
+    srv = http.server.ThreadingHTTPServer(("127.0.0.1", 0), handler)
+    thread = threading.Thread(target=srv.serve_forever, daemon=True)
+    thread.start()
+    return srv
+
+
+class TestProbe(unittest.TestCase):
+    """探针统计与阈值判断。"""
+
+    def test_stable_endpoint_100pct(self):
+        srv = start_server()
+        try:
+            url = f"http://127.0.0.1:{srv.server_port}"
+            probe = AvailabilityProbe([url], timeout_seconds=2)
+            report = probe.run(rounds=10, interval=0)
+        finally:
+            srv.shutdown()
+        self.assertEqual(report.total, 10)
+        self.assertEqual(report.success, 10)
+        self.assertEqual(report.availability, 1.0)
+        self.assertTrue(report.meets_target())
+
+    def test_single_failure_below_threshold(self):
+        srv = start_server(fail_once=True)
+        try:
+            url = f"http://127.0.0.1:{srv.server_port}"
+            probe = AvailabilityProbe([url], timeout_seconds=2)
+            report = probe.run(rounds=500, interval=0)  # 1/500 = 0.2%
+        finally:
+            srv.shutdown()
+        self.assertEqual(len(report.failures), 1)
+        # 1/500 = 0.002 = 99.8% —— 恰好达标（>= target 判定通过）
+        self.assertGreaterEqual(report.availability, report.target)
+        self.assertTrue(report.meets_target())
+        # urllib 对非 200 抛 HTTPError → 记为不可用
+        self.assertFalse(report.failures[0].ok)
+        self.assertIn("503", report.failures[0].detail)
+
+    def test_high_failure_rate_fails_threshold(self):
+        # 构造 50% 失败的端点（fail_mode 每次循环交替：用两个处理器状态不可行，
+        # 改为直接 mock probe_once）
+        probe = AvailabilityProbe(["http://x"], timeout_seconds=1)
+        results = [probe.probe_once.__self__.__class__]  # noqa - 占位
+        from unittest import mock
+        ok_result = mock.MagicMock()
+        ok_result.ok = True
+        bad_result = mock.MagicMock()
+        bad_result.ok = False
+        bad_result.url = "http://x"
+        bad_result.detail = "http-503"
+        bad_result.latency_ms = 1.0
+        # 交替 200/503 → 6 次探测 3 成功 → 50% 可用率，远低于 99.8%
+        with mock.patch.object(probe, "probe_once",
+                               side_effect=[ok_result, bad_result] * 3):
+            report = probe.run(rounds=6, interval=0)
+        self.assertEqual(report.availability, 0.5)
+        self.assertFalse(report.meets_target())
+        self.assertEqual(len(report.failures), 3)
+
+
+if __name__ == "__main__":
+    unittest.main()