EXP: log trims (do not merge)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

run.py

@@ -14,6 +14,12 @@ project_dir = os.path.dirname(os.path.abspath(__file__))
 if project_dir not in sys.path:
     sys.path.insert(0, project_dir)
 
+# Cap glibc's malloc arenas before any thread exists (arenas already made
+# stay): the in-process twin of the unit's MALLOC_ARENA_MAX=2, for units
+# installed before that line. A no-op off glibc. See src/malloc_tuning.py.
+from src import malloc_tuning
+print('EXP cap_arenas=%s' % malloc_tuning.cap_arenas(), flush=True)
+
 # Under systemd the watchdog clock is already running, and start-up (plugin
 # loads, initial updates) takes far longer than the render loop's limit. Widen
 # it before anything slow is imported; the render loop narrows it again once

src/display_controller.py

@@ -37,6 +37,7 @@ from concurrent.futures import ThreadPoolExecutor, as_completed  # pylint: disab
 import pytz
 
 from src import display_watchdog
+from src.malloc_tuning import MallocTrimmer
 from src.display_arbiter import (
     Arbiter, ArbiterInputs, ArbiterState, FramePolicy,
     ScreenPlan, Source, WifiNotice, live_pick, live_takeover, on_demand_bound, rotation_plan,
@@ -4127,6 +4128,7 @@ class DisplayController:
             logger.info(f"Initial mode set to: {self.current_display_mode} (index: {self.current_mode_index}, total modes: {len(self.available_modes)})")
             self._publish_current_mode_state()
             runner = ScreenRunner(_MODULE_CLOCK, _ScreenHost(self), logger)
+            trimmer = MallocTrimmer()
 
             while True:
                 # Arms the watchdog after the first frame -- or after the
@@ -4134,6 +4136,11 @@ class DisplayController:
                 # it from then on.
                 display_watchdog.watchdog.loop_pass()
 
+                # Between screens, nothing being drawn: every few minutes hand
+                # the memory glibc is holding for freed images back to the OS
+                # (src/malloc_tuning.py). A clock read when none is due.
+                trimmer.maybe_trim()
+
                 # Apply plugin enable/disable edits saved via the web UI. The
                 # config-watcher thread only sets the flag; loading/unloading and
                 # rebuilding available_modes happens here on the render thread so

src/malloc_tuning.py

@@ -0,0 +1,128 @@
+"""Keep glibc's malloc from holding on to memory the display has freed.
+
+The display process allocates and frees PIL images and numpy buffers all day
+from a dozen threads. glibc gives each allocating thread its own malloc arena
+(up to 8 x CPU count) and returns little of what is freed inside them to the
+OS, so resident memory climbs for hours while the live data stays flat. Two
+in-process remedies, both standard library only (ctypes) and both no-ops off
+Linux/glibc:
+
+* :func:`cap_arenas` -- ``mallopt(M_ARENA_MAX, 2)``, the in-process twin of the
+  unit's ``Environment=MALLOC_ARENA_MAX=2``. Units installed before that line
+  existed never got it (systemd runs the copy in /etc/systemd/system), so the
+  process applies it itself. Call it before any other thread starts: arenas
+  already created stay. A ``MALLOC_ARENA_MAX`` set in the environment wins.
+* :class:`MallocTrimmer` -- ``malloc_trim(0)`` at most every few minutes,
+  called from the render loop between screens, where no frame is being drawn.
+  glibc 2.8+ releases free pages from the middle of every arena, not only the
+  top of the main heap.
+
+Without glibc (macOS, Windows, musl, the dev server on any of them) nothing is
+loaded and every call returns False.
+"""
+import ctypes
+import logging
+import os
+import sys
+import time
+from typing import Any, Callable, Optional
+
+logger = logging.getLogger(__name__)
+
+#: glibc's mallopt() parameter number for the arena cap (malloc.h).
+M_ARENA_MAX = -8
+
+#: The arena cap applied when the environment does not set one; the same value
+#: as the unit's ``MALLOC_ARENA_MAX``.
+DEFAULT_ARENA_MAX = 2
+
+#: Seconds between malloc_trim() calls. A trim takes about 1-20 ms on a Pi 4,
+#: so this keeps it far from frame timing while still returning memory long
+#: before it piles up.
+TRIM_INTERVAL_SECONDS = 300.0
+
+_UNLOADED = object()
+_libc: Any = _UNLOADED
+
+
+def _load_libc() -> Optional[Any]:
+    """The process's C library if it is glibc with malloc_trim, else None."""
+    global _libc
+    if _libc is _UNLOADED:
+        _libc = None
+        if sys.platform.startswith('linux'):
+            try:
+                libc = ctypes.CDLL(None)
+                # gnu_get_libc_version is glibc-only: musl also lacks
+                # malloc_trim, but this says why without guessing.
+                libc.gnu_get_libc_version
+                libc.malloc_trim.argtypes = [ctypes.c_size_t]
+                libc.malloc_trim.restype = ctypes.c_int
+                libc.mallopt.argtypes = [ctypes.c_int, ctypes.c_int]
+                libc.mallopt.restype = ctypes.c_int
+                _libc = libc
+            except (OSError, AttributeError, TypeError):
+                logger.debug("glibc malloc controls unavailable", exc_info=True)
+    return _libc
+
+
+def cap_arenas(max_arenas: int = DEFAULT_ARENA_MAX) -> bool:
+    """Cap glibc's malloc arenas at ``max_arenas``. True when the cap was set.
+
+    Skipped when ``MALLOC_ARENA_MAX`` is in the environment: glibc has read it
+    already, and an operator who set it chose that value.
+    """
+    if os.environ.get('MALLOC_ARENA_MAX'):
+        return False
+    libc = _load_libc()
+    if libc is None:
+        return False
+    try:
+        return bool(libc.mallopt(M_ARENA_MAX, int(max_arenas)))
+    except Exception:  # pylint: disable=broad-except
+        logger.debug("mallopt(M_ARENA_MAX) failed", exc_info=True)
+        return False
+
+
+class MallocTrimmer:
+    """Calls ``malloc_trim(0)`` at most once per ``interval`` seconds.
+
+    :meth:`maybe_trim` is meant for an idle point of the render loop; it costs
+    one clock read when no trim is due. The first trim comes one interval
+    after construction, so start-up's allocations have settled.
+    """
+
+    def __init__(self, interval: float = TRIM_INTERVAL_SECONDS,
+                 clock: Callable[[], float] = time.monotonic) -> None:
+        self._interval = interval
+        self._clock = clock
+        self._libc = _load_libc()
+        self._next = clock() + interval
+
+    @property
+    def available(self) -> bool:
+        return self._libc is not None
+
+    def maybe_trim(self) -> bool:
+        """Trim if one is due. True when malloc_trim ran and released memory."""
+        if self._libc is None:
+            return False
+        now = self._clock()
+        if now < self._next:
+            return False
+        self._next = now + self._interval
+        try:
+            released = bool(self._libc.malloc_trim(0))
+        except Exception:  # pylint: disable=broad-except
+            logger.debug("malloc_trim failed; not trying again", exc_info=True)
+            self._libc = None
+            return False
+        def _rss():
+            try:
+                with open('/proc/self/statm') as f:
+                    return int(f.read().split()[1]) * 4096 // 1024
+            except Exception:
+                return -1
+        logger.info("EXP malloc_trim(0) took %.1f ms, released=%s rss_kb_after=%d",
+                     (self._clock() - now) * 1000.0, released, _rss())
+        return released