commit 30de0d61ef146d01eb48208ae15beac59dcf905f
Author: Sun Ruoxi <sunruoxi@4paradigm.com>
Date:   Thu Aug 6 11:05:00 2026 +0800

    feat: add container restart storage test

diff --git a/.dockerignore b/.dockerignore
new file mode 100644
index 0000000..35cdaf3
--- /dev/null
+++ b/.dockerignore
@@ -0,0 +1,2 @@
+.git
+README.md
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..c9f16ab
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,14 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+COPY test_restart.py /app/test_restart.py
+
+ENV PORT=8080
+ENV RUN_SECONDS=60
+
+EXPOSE 8080
+
+HEALTHCHECK --interval=10s --timeout=3s --start-period=3s --retries=3 \
+    CMD python -c "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8080/health', timeout=2)" || exit 1
+
+CMD ["python", "/app/test_restart.py"]
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..2406831
--- /dev/null
+++ b/README.md
@@ -0,0 +1,24 @@
+# Container restart file test
+
+用于测试当前平台在程序正常执行完成、退出码为 `0`、随后自动重启容器时，容器内 `/app` 文件是否保留。
+
+镜像启动时会检查并写入 `/app/restart-marker.txt`，在 8080 端口提供 `/health`，默认运行 60 秒后以退出码 0 正常退出。
+
+构建并推送：
+
+```bash
+docker build -t <registry>/k8s-restart-storage-test:<tag> .
+docker push <registry>/k8s-restart-storage-test:<tag>
+```
+
+平台每次启动时查看日志。如果每次都是：
+
+```text
+marker_existed_before_start=false
+```
+
+表示上次写入的文件已经丢失。如果第二次及之后显示 `true`，表示平台的这种重启方式保留了容器内文件。
+
+日志中的 `pod_name` 相同通常表示同一个 Pod 内重启，名称改变表示创建了新 Pod。平台如果注入了 `POD_UID` 环境变量，日志也会一并打印。
+
+可通过环境变量 `RUN_SECONDS` 调整正常退出前的运行秒数。
diff --git a/test_restart.py b/test_restart.py
new file mode 100644
index 0000000..00fa319
--- /dev/null
+++ b/test_restart.py
@@ -0,0 +1,68 @@
+#!/usr/bin/env python3
+"""提供健康检查，并验证平台重启容器后 /app 中的文件是否保留。"""
+
+import json
+import os
+import socket
+import sys
+import threading
+import time
+from datetime import datetime, timezone
+from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
+from pathlib import Path
+
+
+PORT = int(os.getenv("PORT", "8080"))
+RUN_SECONDS = int(os.getenv("RUN_SECONDS", "60"))
+MARKER = Path(os.getenv("MARKER_FILE", "/app/restart-marker.txt"))
+
+
+class Handler(BaseHTTPRequestHandler):
+    def do_GET(self) -> None:
+        if self.path != "/health":
+            self.send_error(404)
+            return
+        payload = json.dumps({"status": "ok"}).encode()
+        self.send_response(200)
+        self.send_header("Content-Type", "application/json")
+        self.send_header("Content-Length", str(len(payload)))
+        self.end_headers()
+        self.wfile.write(payload)
+
+    def log_message(self, _format: str, *_args: object) -> None:
+        return
+
+
+def main() -> int:
+    now = datetime.now(timezone.utc).astimezone().isoformat()
+    pod_name = os.getenv("POD_NAME", socket.gethostname())
+    pod_uid = os.getenv("POD_UID", "unknown")
+    existed = MARKER.exists()
+    previous = MARKER.read_text().strip() if existed else "<missing>"
+
+    print("=" * 70, flush=True)
+    print(f"time={now}", flush=True)
+    print(f"pod_name={pod_name}", flush=True)
+    print(f"pod_uid={pod_uid}", flush=True)
+    print(f"marker={MARKER}", flush=True)
+    print(f"marker_existed_before_start={str(existed).lower()}", flush=True)
+    print(f"marker_previous_content={previous}", flush=True)
+
+    MARKER.parent.mkdir(parents=True, exist_ok=True)
+    MARKER.write_text(f"pod={pod_name} uid={pod_uid} written_at={now}\n")
+    print("marker_written=true", flush=True)
+
+    server = ThreadingHTTPServer(("0.0.0.0", PORT), Handler)
+    server_thread = threading.Thread(target=server.serve_forever, daemon=True)
+    server_thread.start()
+    print(f"health_url=http://0.0.0.0:{PORT}/health", flush=True)
+    print(f"will_exit_normally_after={RUN_SECONDS}s", flush=True)
+    time.sleep(RUN_SECONDS)
+    server.shutdown()
+    server.server_close()
+    print("program completed; exiting normally with code 0", flush=True)
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())