From d3ce89f22849d262a76c1eecab02b4ffb9647bde Mon Sep 17 00:00:00 2001
From: dev <dev@remuxarr>
Date: Fri, 15 May 2026 17:02:09 +0200
Subject: [PATCH] perf: stale-while-revalidate cache + startup pre-warm

If DB has any concerts data (even expired), return it immediately and
refresh in background. Start pre-warming at container startup so the
scrape runs before the first user request.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 arte_api.py | 47 +++++++++++++++++++++++++++++++----------------
 main.py     |  3 ++-
 2 files changed, 33 insertions(+), 17 deletions(-)

diff --git a/arte_api.py b/arte_api.py
index 6321bcb..f43cedc 100644
--- a/arte_api.py
+++ b/arte_api.py
@@ -15,6 +15,7 @@ CACHE_TTL = 6 * 3600
 DB_PATH = "data/arte_dl.db"
 _cache: dict = {"data": [], "ts": 0}
 _fetch_lock: asyncio.Lock | None = None
+_refresh_task: asyncio.Task | None = None
 
 
 def _get_fetch_lock() -> asyncio.Lock:
@@ -209,24 +210,12 @@ async def get_concerts_by_category(category: str) -> list[dict]:
     return [c for c in data if category in (c.get("categories") or [])]
 
 
-async def get_all_concerts() -> list[dict]:
-    now = time.time()
-    if _cache["data"] and now - _cache["ts"] < CACHE_TTL:
-        return _cache["data"]
-
-    # Try SQLite cache before acquiring the lock
-    db_data, db_ts = _load_db_cache()
-    if db_data and now - db_ts < CACHE_TTL:
-        logger.info("Concerts cache loaded from DB (%d concerts)", len(db_data))
-        _cache["data"] = db_data
-        _cache["ts"] = db_ts
-        return _cache["data"]
-
-    # Lock prevents multiple concurrent scrapes (thundering herd)
+async def _do_refresh():
+    """Full scrape under lock; updates in-memory + DB cache."""
+    global _refresh_task
     async with _get_fetch_lock():
-        # Re-check after acquiring lock — another coroutine may have populated the cache
         if _cache["data"] and time.time() - _cache["ts"] < CACHE_TTL:
-            return _cache["data"]
+            return
         loop = asyncio.get_event_loop()
         data = await loop.run_in_executor(None, _fetch_all_sync)
         if data:
@@ -234,6 +223,32 @@ async def get_all_concerts() -> list[dict]:
             _cache["data"] = data
             _cache["ts"] = ts
             _save_db_cache(data, ts)
+            logger.info("Cache refreshed: %d concerts", len(data))
+    _refresh_task = None
+
+
+async def get_all_concerts() -> list[dict]:
+    global _refresh_task
+    now = time.time()
+
+    # In-memory cache hit
+    if _cache["data"] and now - _cache["ts"] < CACHE_TTL:
+        return _cache["data"]
+
+    # Try DB cache — return immediately even if stale, refresh in background
+    db_data, db_ts = _load_db_cache()
+    if db_data:
+        _cache["data"] = db_data
+        _cache["ts"] = db_ts
+        logger.info("Concerts loaded from DB cache (%d concerts)", len(db_data))
+        if now - db_ts >= CACHE_TTL:
+            # Stale — serve now, refresh silently in background
+            if _refresh_task is None or _refresh_task.done():
+                _refresh_task = asyncio.create_task(_do_refresh())
+        return _cache["data"]
+
+    # No cache at all — must scrape synchronously (first run or cleared DB)
+    await _do_refresh()
     return _cache["data"]
 
 
diff --git a/main.py b/main.py
index 559f251..7371862 100644
--- a/main.py
+++ b/main.py
@@ -11,7 +11,7 @@ from fastapi.staticfiles import StaticFiles
 from fastapi.templating import Jinja2Templates
 from pydantic import BaseModel
 
-from arte_api import fetch_concerts, get_concerts_by_category, invalidate_cache, CATEGORIES
+from arte_api import fetch_concerts, get_all_concerts, get_concerts_by_category, invalidate_cache, CATEGORIES
 from downloader import DownloadManager
 
 logging.basicConfig(level=logging.INFO)
@@ -56,6 +56,7 @@ async def lifespan(app: FastAPI):
     tasks = [
         asyncio.create_task(dm.start_worker()),
         asyncio.create_task(_auto_dl_loop()),
+        asyncio.create_task(get_all_concerts()),   # pre-warm cache at startup
     ]
     yield
     for t in tasks: