Joseph Doherty
fc08892eb3
Root cause: pymodbus 3.13's `pymodbus.simulator` console script hard-codes asyncio.run(run_main(), debug=True). Debug mode captures a traceback per scheduled callback and logs callbacks slower than 100 ms (the "took 0.146 seconds" lines in #909). Side by side on the shared docker host (closed-loop FC03 clients, 2 s deadline): 100 clients got ~120-170 req/s, p99 1.6-1.9 s with client timeouts in debug mode vs ~2400 req/s, p99 ~135 ms without it. The shared sim also carries the docker-dev rig's 49 Modbus drivers on each of central-1/central-2 (98 sockets, ~220 req/s at idle), which is above the debug-mode capacity, so a test run on top was answered late ("Cancel send, because not connected!") and timed out. - run_simulator.py: same CLI as pymodbus.simulator, debug=False, plus a watchdog thread that exits after 3 failed FC03 probes so restart: unless-stopped replaces the container (docker has no restart-on-unhealthy). - fc3_probe.py: stdlib FC03 read with a deadline (MBAP or RTU framing); the compose healthcheck. - docker-compose.yml: shared anchor for every pymodbus service: new entrypoint, `project: lmxopcua` label, restart: unless-stopped, healthcheck, bounded json-file logs. - README: why, the numbers, and how to diagnose load.
90 lines
3.4 KiB
Python
90 lines
3.4 KiB
Python
#!/usr/bin/env python3
|
|
"""Liveness probe for the pymodbus simulator: one FC03 read with a hard deadline (#909).
|
|
|
|
A TCP connect is not enough. The #909 fixture accepted connections while answering
|
|
every request after the client had timed out, so a connect-only check stayed green.
|
|
This probe sends a real FC03 read and passes only on a timely, well-formed reply.
|
|
A Modbus exception reply also passes: it proves the request loop is serving.
|
|
|
|
Pure stdlib, so it runs in the image without extra packages. It is used two ways:
|
|
* as the compose ``healthcheck`` (exit code 0 = healthy, 1 = unhealthy);
|
|
* imported by ``run_simulator.py``, whose watchdog exits the container after
|
|
repeated failures so ``restart: unless-stopped`` brings up a fresh one.
|
|
|
|
Usage: fc3_probe.py [--port 5020] [--framer socket|rtu] [--deadline 3]
|
|
"""
|
|
import argparse
|
|
import socket
|
|
import struct
|
|
import sys
|
|
import time
|
|
|
|
|
|
def _crc16(data: bytes) -> int:
|
|
crc = 0xFFFF
|
|
for b in data:
|
|
crc ^= b
|
|
for _ in range(8):
|
|
crc = (crc >> 1) ^ 0xA001 if crc & 1 else crc >> 1
|
|
return crc
|
|
|
|
|
|
def _recv_exact(sock: socket.socket, n: int, end: float) -> bytes:
|
|
buf = b""
|
|
while len(buf) < n:
|
|
remaining = end - time.monotonic()
|
|
if remaining <= 0:
|
|
raise TimeoutError("deadline passed")
|
|
sock.settimeout(remaining)
|
|
chunk = sock.recv(n - len(buf))
|
|
if not chunk:
|
|
raise ConnectionError("closed mid-reply")
|
|
buf += chunk
|
|
return buf
|
|
|
|
|
|
def probe(host: str = "127.0.0.1", port: int = 5020, framer: str = "socket",
|
|
deadline: float = 3.0, unit: int = 1, address: int = 0) -> None:
|
|
"""Raise on failure; return on a timely, well-formed FC03 reply (data or exception)."""
|
|
end = time.monotonic() + deadline
|
|
pdu = struct.pack(">BHH", 3, address, 1)
|
|
with socket.create_connection((host, port), timeout=deadline) as sock:
|
|
if framer == "rtu":
|
|
frame = bytes([unit]) + pdu
|
|
sock.sendall(frame + struct.pack("<H", _crc16(frame)))
|
|
head = _recv_exact(sock, 2, end) # unit, fc
|
|
if head[1] & 0x80:
|
|
_recv_exact(sock, 3, end) # exc code + CRC
|
|
else:
|
|
count = _recv_exact(sock, 1, end)[0]
|
|
_recv_exact(sock, count + 2, end) # data + CRC
|
|
return
|
|
tid = int(time.monotonic() * 1000) & 0xFFFF
|
|
sock.sendall(struct.pack(">HHHB", tid, 0, len(pdu) + 1, unit) + pdu)
|
|
header = _recv_exact(sock, 7, end)
|
|
rtid, _, length, _ = struct.unpack(">HHHB", header)
|
|
if rtid != tid:
|
|
raise ValueError(f"transaction id {rtid} != {tid}")
|
|
if length < 2:
|
|
raise ValueError(f"MBAP length {length} too small")
|
|
_recv_exact(sock, length - 1, end)
|
|
|
|
|
|
def main() -> int:
|
|
ap = argparse.ArgumentParser()
|
|
ap.add_argument("--host", default="127.0.0.1")
|
|
ap.add_argument("--port", type=int, default=5020)
|
|
ap.add_argument("--framer", choices=["socket", "rtu"], default="socket")
|
|
ap.add_argument("--deadline", type=float, default=3.0)
|
|
args = ap.parse_args()
|
|
try:
|
|
probe(args.host, args.port, args.framer, args.deadline)
|
|
except Exception as exc: # noqa: BLE001 - any failure is "unhealthy"
|
|
print(f"FC03 probe failed: {type(exc).__name__}: {exc}", file=sys.stderr)
|
|
return 1
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|