Merge 66d1e31005 into d982b3a782

* perf(util): use monotonic clock and bounded deque in EventsPerSecond

EventsPerSecond is updated on every captured frame, every detection and
every processed frame across all cameras and detectors. The previous
implementation derived timestamps from datetime.now().timestamp() (wall
clock), so an NTP or manual clock adjustment could skew the rolling-window
expiry; it also stored timestamps in a list and expired them with
del self._timestamps[0] (O(n) per removal) plus a periodic slice-copy to
cap growth.

Switch to time.monotonic() for the interval math (correct by construction
and immune to wall-clock jumps) and a collections.deque(maxlen=...) so
expiry is O(1) (popleft) and retention is bounded automatically. This
mirrors the deque-based expiry already used in video/ffmpeg.py and
watchdog.py. Observable output is unchanged.

Adds frigate/test/test_builtin.py covering rate calculation, window
expiry and the memory bound.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test: drop test_timestamps_are_memory_bounded

It only asserted that deque(maxlen=) caps length, which is stdlib behavior
rather than something this change needs to verify.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

docker/tensorrt/requirements-amd64.txt

@@ -1,6 +1,6 @@
 # Nvidia ONNX Runtime GPU Support
 --extra-index-url 'https://pypi.nvidia.com'
-cython==3.0.*; platform_machine == 'x86_64'
+cython==3.2.*; platform_machine == 'x86_64'
 nvidia-cuda-cupti-cu12==12.8.90; platform_machine == 'x86_64'
 nvidia-cublas-cu12==12.8.4.1; platform_machine == 'x86_64'
 nvidia-cudnn-cu12==9.8.0.87; platform_machine == 'x86_64'

frigate/api/preview.py

@@ -1,7 +1,9 @@
 """Preview apis."""
 
+import bisect
 import logging
 import os
+import threading
 from datetime import datetime, timedelta, timezone
 
 import pytz
@@ -133,6 +135,32 @@ def preview_hour(
     return preview_ts(camera_name, start_ts, end_ts, allowed_cameras)
 
 
+# cache one sorted listing of the shared preview_frames dir
+_preview_listing_lock = threading.Lock()
+_preview_listing_cache: tuple[float, list[str]] = (-1.0, [])
+
+
+def _get_preview_frame_listing(preview_dir: str) -> list[str]:
+    """Return the sorted preview_frames listing, cached until the dir changes."""
+    global _preview_listing_cache
+
+    # mtime bumps when a frame is added or removed, invalidating the cache
+    mtime = os.stat(preview_dir).st_mtime
+    cached_mtime, files = _preview_listing_cache
+    if mtime == cached_mtime:
+        return files
+
+    with _preview_listing_lock:
+        # another thread may have refreshed the cache while we waited
+        cached_mtime, files = _preview_listing_cache
+        if mtime == cached_mtime:
+            return files
+
+        files = sorted(entry.name for entry in os.scandir(preview_dir))
+        _preview_listing_cache = (mtime, files)
+        return files
+
+
 @router.get(
     "/preview/{camera_name}/start/{start_ts}/end/{end_ts}/frames",
     response_model=PreviewFramesResponse,
@@ -149,23 +177,15 @@ def get_preview_frames_from_cache(camera_name: str, start_ts: float, end_ts: flo
     start_file = f"{file_start}{start_ts}.{PREVIEW_FRAME_TYPE}"
     end_file = f"{file_start}{end_ts}.{PREVIEW_FRAME_TYPE}"
 
-    camera_files = [
+    files = _get_preview_frame_listing(preview_dir)
-        entry.name
+
-        for entry in os.scandir(preview_dir)
+    # a camera's frames form a contiguous slice of the sorted listing;
-        if entry.name.startswith(file_start)
+    # bisect locates it without scanning the whole directory
+    left = bisect.bisect_left(files, start_file)
+    right = bisect.bisect_right(files, end_file)
+    selected_previews = [
+        file for file in files[left:right] if file.startswith(file_start)
     ]
-    camera_files.sort()
-
-    selected_previews = []
-
-    for file in camera_files:
-        if file < start_file:
-            continue
-
-        if file > end_file:
-            break
-
-        selected_previews.append(file)
 
     return JSONResponse(
         content=selected_previews,

frigate/test/test_builtin.py

@@ -0,0 +1,41 @@
+"""Tests for frigate.util.builtin helpers."""
+
+import unittest
+from unittest.mock import patch
+
+from frigate.util.builtin import EventsPerSecond
+
+
+class TestEventsPerSecond(unittest.TestCase):
+    def test_eps_is_zero_before_any_events(self) -> None:
+        eps = EventsPerSecond()
+        with patch("frigate.util.builtin.time.monotonic", return_value=100.0):
+            self.assertEqual(eps.eps(), 0.0)
+
+    def test_eps_counts_events_in_window(self) -> None:
+        eps = EventsPerSecond(last_n_seconds=10)
+        clock = [1000.0]
+        with patch("frigate.util.builtin.time.monotonic", side_effect=lambda: clock[0]):
+            eps.start()
+            # one event per second for five seconds
+            for _ in range(5):
+                clock[0] += 1.0
+                eps.update()
+            # five events over the five seconds since start
+            self.assertAlmostEqual(eps.eps(), 1.0)
+
+    def test_old_timestamps_expire_from_window(self) -> None:
+        eps = EventsPerSecond(last_n_seconds=10)
+        clock = [0.0]
+        with patch("frigate.util.builtin.time.monotonic", side_effect=lambda: clock[0]):
+            eps.start()
+            for _ in range(10):
+                clock[0] += 1.0
+                eps.update()
+            # jump well past the window so every timestamp ages out
+            clock[0] += 100.0
+            self.assertEqual(eps.eps(), 0.0)
+
+
+if __name__ == "__main__":
+    unittest.main()

frigate/util/builtin.py

@@ -2,7 +2,6 @@
 
 import ast
 import copy
-import datetime
 import logging
 import math
 import multiprocessing.queues
@@ -10,7 +9,9 @@ import queue
 import re
 import shlex
 import struct
+import time
 import urllib.parse
+from collections import deque
 from collections.abc import Mapping
 from multiprocessing.managers import ValueProxy
 from pathlib import Path
@@ -32,23 +33,20 @@ class EventsPerSecond:
         self._start = None
         self._max_events = max_events
         self._last_n_seconds = last_n_seconds
-        self._timestamps = []
+        self._timestamps: deque[float] = deque(maxlen=max_events)
 
     def start(self) -> None:
-        self._start = datetime.datetime.now().timestamp()
+        self._start = time.monotonic()
 
     def update(self) -> None:
-        now = datetime.datetime.now().timestamp()
+        now = time.monotonic()
         if self._start is None:
             self._start = now
         self._timestamps.append(now)
-        # truncate the list when it goes 100 over the max_size
-        if len(self._timestamps) > self._max_events + 100:
-            self._timestamps = self._timestamps[(1 - self._max_events) :]
         self.expire_timestamps(now)
 
     def eps(self) -> float:
-        now = datetime.datetime.now().timestamp()
+        now = time.monotonic()
         if self._start is None:
             self._start = now
         # compute the (approximate) events in the last n seconds
@@ -63,7 +61,7 @@ class EventsPerSecond:
     def expire_timestamps(self, now: float) -> None:
         threshold = now - self._last_n_seconds
         while self._timestamps and self._timestamps[0] < threshold:
-            del self._timestamps[0]
+            self._timestamps.popleft()
 
 
 class InferenceSpeed: