rick/LEDMatrix
1
0
Fork 0
mirror of https://github.com/ChuckBuilds/LEDMatrix.git synced 2026-08-14 15:18:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

test(sync): cover the display sync protocol, and fix what that surfaced

Browse Source 
DisplaySyncManager had no tests at all — it appeared in the suite only as
a MagicMock() stand-in, so none of its framing, handshake, or socket
handling was ever exercised. Writing that coverage surfaced three bugs.

Both receive loops caught the generic Exception and immediately retried.
A socket left in a bad state raises on every call, so the thread spun at
100% CPU logging the same line; the reverted-code run of the new
regression test takes 24 seconds where the fixed one takes 0.2. Both now
back off briefly before retrying.

The follower dispatched on `data[:8] == _RAW_MAGIC or len(data) > 512`.
That size threshold is not part of either wire format: a control message
over 512 bytes — a hello_ack carrying a long incompatibility error, for
instance — went to the image decoder and was dropped, and a raw frame
under 512 bytes went to the JSON parser. Both formats are already
self-describing, so dispatch on the magic prefix and treat a JSON parse
failure as the legacy unmarked PNG, with the shared frame bookkeeping
factored into _handle_received_frame().

_oversized_frame_warned was created on first use through
getattr(self, ..., False) rather than in __init__, alone among the
instance attributes.

75 tests: role parsing, the hello compatibility matrix, watchdog
timeouts, both receive loops, the TCP image server's length and
dimension caps and decompression-bomb guard, status shape per role, and
one end-to-end loopback handshake so the wire format is exercised for
real and not only against mocks.

Co-Authored-By: Claude <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NohXi78cwsAKtN1sCfxjUh
This commit is contained in:
Claude
2026-08-13 13:37:01 +00:00
parent 9cf30bbbef
commit 062bdf691f
2 changed files with 869 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/common/sync_manager.py
+42 -27
View File
@@ -101,6 +101,7 @@ class DisplaySyncManager:
self._peer_chain: int = 0
self._last_heartbeat_time: float = 0.0
self._leader_width: int = 0 # set by display_controller after init
self._oversized_frame_warned: bool = False
# Follower state
self._follower_state = FollowerState.STANDALONE
@@ -174,6 +175,10 @@ class DisplaySyncManager:
continue
except Exception as exc:
self.logger.debug("Sync leader recv error: %s", exc)
# Brief backoff: a socket left in a bad state raises
# immediately, which would otherwise spin this thread at
# 100% CPU logging the same error.
time.sleep(0.1)
def _handle_hello(self, msg: dict, sender_ip: str) -> None:
hw = self._hw_config
@@ -396,7 +401,7 @@ class DisplaySyncManager:
data = header + arr.tobytes()
if len(data) <= 65000:
self._send_sock.sendto(data, (self._peer_ip, self.port))
elif not getattr(self, '_oversized_frame_warned', False):
elif not self._oversized_frame_warned:
self._oversized_frame_warned = True
self.logger.warning(
"Sync: frame too large for UDP (%d bytes, max 65000) — "
@@ -451,41 +456,44 @@ class DisplaySyncManager:
)
self.write_status_file()
def _handle_received_frame(self, img: Image.Image, sender_ip: str) -> None:
"""Record a decoded leader frame and enter follower mode if needed."""
with self._frame_lock:
self._latest_frame = img
self._last_leader_frame_time = time.time()
self._leader_ip = sender_ip
if self._follower_state == FollowerState.STANDALONE:
self._follower_state = FollowerState.FOLLOWER
self.logger.info(
"Sync: leader active at %s — switching to follower mode",
sender_ip,
)
self.write_status_file()
def _follower_recv_loop(self) -> None:
while self._running:
try:
data, addr = self._recv_sock.recvfrom(65535)
sender_ip = addr[0]
if data[:8] == _RAW_MAGIC or len(data) > 512:
# Frame data: prefer magic-tagged raw RGB; fall back to legacy PNG
if data[:8] == _RAW_MAGIC:
# Magic-tagged raw RGB frame — self-describing, no guessing.
try:
if data[:8] == _RAW_MAGIC:
w, h = _RAW_HEADER.unpack(data[8:12])
raw = data[12:]
img = Image.frombuffer(
"RGB", (w, h), raw, "raw", "RGB", 0, 1
)
else:
# Fallback: try legacy PNG
img = Image.open(io.BytesIO(data))
img.load()
with self._frame_lock:
self._latest_frame = img
self._last_leader_frame_time = time.time()
self._leader_ip = sender_ip
if self._follower_state == FollowerState.STANDALONE:
self._follower_state = FollowerState.FOLLOWER
self.logger.info(
"Sync: leader active at %s — switching to follower mode",
sender_ip,
)
self.write_status_file()
w, h = _RAW_HEADER.unpack(data[8:12])
raw = data[12:]
img = Image.frombuffer(
"RGB", (w, h), raw, "raw", "RGB", 0, 1
)
self._handle_received_frame(img, sender_ip)
except Exception as exc:
self.logger.debug("Sync: frame decode error: %s", exc)
else:
# Control message
# No magic prefix: try control-message JSON, and treat a
# parse failure as a legacy (pre-magic) PNG frame. Both
# wire formats are self-describing, so no size heuristic
# is needed — a >512-byte control message used to be
# misrouted into image decode and silently dropped.
try:
msg = json.loads(data.decode("utf-8"))
t = msg.get("t")
@@ -518,12 +526,19 @@ class DisplaySyncManager:
if self._on_new_cycle:
self._on_new_cycle()
except (json.JSONDecodeError, UnicodeDecodeError, KeyError):
pass
# Not a control message — try legacy PNG frame.
try:
img = Image.open(io.BytesIO(data))
img.load()
self._handle_received_frame(img, sender_ip)
except Exception as exc:
self.logger.debug("Sync: frame decode error: %s", exc)
except socket.timeout:
continue
except Exception as exc:
self.logger.debug("Sync follower recv error: %s", exc)
time.sleep(0.1)
def _follower_announce_loop(self) -> None:
hw = self._hw_config