Keep GSMTAP capture alive + server-side liveness logging

The GSMTAP capture thread died silently whenever a single non-SIM or
truncated GSMTAP datagram arrived (read_packet() raises ValueError,
uncaught in the loop, killing the daemon thread while UDP kept
flowing) — matching the "stops listening after a sniffer restart"
symptom.

Fixes:
- GsmtapListener.iter_messages() now catches ValueError/struct.error
  from read_packet(), drops the offending datagram (counted via a new
  `dropped` counter) and keeps listening.
- CaptureManager._capture_loop() guards the DB insert so a transient
  error can't kill the thread; a top-level guard logs
  "ERROR: capture thread stopped on error …" + traceback and clears
  the session so /api/status no longer reports a stuck "active".
- Server now logs capture liveness to stderr: "Capture started", a
  periodic "Capture alive: session=N messages=M bytes=B dropped=D"
  heartbeat (default every 60 s, configurable via log_interval), and
  "Capture stopped" (or "empty session discarded").

Tests: +5 (listener survives non-SIM/short packet, capture loop
survives insert error, logs stop-on-error, heartbeat+stop log).
Stays on 1.22.0 (backend-only).
This commit is contained in:
catarrh committed 2026-08-26 22:21:14 +03:00
1 parent 79acb3773f
commit 51e1b4ae08
3 files changed
+216 -4

No files matched your search

+7
View File
@@ -113,6 +113,13 @@ simtrace2-pysniff-server --capture direct
simtrace2-pysniff-server --capture disabled simtrace2-pysniff-server --capture disabled
``` ```
The server logs its capture liveness to stderr: `Capture started` on
begin, a periodic `Capture alive: session=N messages=M bytes=B dropped=D`
heartbeat, and `Capture stopped` (or `ERROR: capture thread stopped on
error …` if the capture thread died unexpectedly). A mis-framed or
non-SIM GSMTAP datagram is dropped and counted (`dropped`) rather than
silently killing the capture.
The GSMTAP listener also accepts the **sigrok-iso7816-stream** decoder The GSMTAP listener also accepts the **sigrok-iso7816-stream** decoder
(https://github.com/anttro/sigrok_iso7816_stream) — an FX2-logic-analyzer (https://github.com/anttro/sigrok_iso7816_stream) — an FX2-logic-analyzer
passive SIM sniffer that emits the same GSMTAP-SIM format on UDP 4729. Its passive SIM sniffer that emits the same GSMTAP-SIM format on UDP 4729. Its
+76 -4
View File
@@ -1,7 +1,10 @@
"""Capture backends: GSMTAP listener and direct SIMtrace2 sniffer.""" """Capture backends: GSMTAP listener and direct SIMtrace2 sniffer."""
import time import struct
import sys
import threading import threading
import time
import traceback
from ..gsmtap import (GsmtapReceiver, GSMTAP_SIM_ATR, from ..gsmtap import (GsmtapReceiver, GSMTAP_SIM_ATR,
GSMTAP_SIM_RST_EVENT, GSMTAP_SIM_VCC_EVENT) GSMTAP_SIM_RST_EVENT, GSMTAP_SIM_VCC_EVENT)
@@ -24,17 +27,33 @@ class GsmtapListener:
def __init__(self, bind_port=4729): def __init__(self, bind_port=4729):
self._receiver = GsmtapReceiver(bind_port=bind_port) self._receiver = GsmtapReceiver(bind_port=bind_port)
self._running = False self._running = False
self._dropped = 0
def start(self): def start(self):
self._running = True self._running = True
self._dropped = 0
def stop(self): def stop(self):
self._running = False self._running = False
self._receiver.close() self._receiver.close()
@property
def dropped(self):
return self._dropped
def iter_messages(self): def iter_messages(self):
while self._running: while self._running:
try:
sub_type, data, flags = self._receiver.read_packet() sub_type, data, flags = self._receiver.read_packet()
except (ValueError, struct.error) as e:
# A malformed or non-SIM GSMTAP datagram (a different
# GSMTAP packet type, a truncated frame, …) must not kill
# the whole capture — drop it and keep listening.
self._dropped += 1
if self._dropped <= 1 or self._dropped % 100 == 0:
print(f'GSMTAP: dropped packet ({self._dropped}): {e}',
file=sys.stderr)
continue
if sub_type is None: if sub_type is None:
continue continue
yield gsmtap_msg_type(sub_type), data, flags yield gsmtap_msg_type(sub_type), data, flags
@@ -75,13 +94,18 @@ class DirectSniffer:
class CaptureManager: class CaptureManager:
def __init__(self, backend, db): def __init__(self, backend, db, log_interval=60.0):
self._backend = backend self._backend = backend
self._db = db self._db = db
self._session_id = None self._session_id = None
self._thread = None self._thread = None
self._log_thread = None
self._stop_event = threading.Event()
self._start_time = 0.0 self._start_time = 0.0
self._latest_msg_id = 0 self._latest_msg_id = 0
self._msg_count = 0
self._byte_count = 0
self._log_interval = log_interval
@property @property
def active(self): def active(self):
@@ -115,32 +139,80 @@ class CaptureManager:
self._session_id = self._db.create_session(mode) self._session_id = self._db.create_session(mode)
self._start_time = time.monotonic() self._start_time = time.monotonic()
self._latest_msg_id = 0 self._latest_msg_id = 0
self._msg_count = 0
self._byte_count = 0
self._backend.start() self._backend.start()
self._thread = threading.Thread(target=self._capture_loop, daemon=True) self._thread = threading.Thread(target=self._capture_loop, daemon=True)
self._thread.start() self._thread.start()
self._stop_event.clear()
print(f'Capture started (mode={mode}, session={self._session_id})',
file=sys.stderr)
self._log_thread = threading.Thread(target=self._log_loop, daemon=True)
self._log_thread.start()
return self._session_id return self._session_id
def stop_session(self): def stop_session(self):
if self._session_id is None: if self._session_id is None:
return None return None
self._stop_event.set()
self._backend.stop() self._backend.stop()
if self._thread is not None: if self._thread is not None:
self._thread.join(timeout=2.0) self._thread.join(timeout=2.0)
if self._log_thread is not None:
self._log_thread.join(timeout=2.0)
sid = self._session_id sid = self._session_id
self._session_id = None self._session_id = None
self._start_time = 0.0 self._start_time = 0.0
if self._db.count_messages(sid) == 0: empty = self._db.count_messages(sid) == 0
if empty:
self._db.delete_session(sid) self._db.delete_session(sid)
print(f'Capture stopped: empty session discarded (session={sid})',
file=sys.stderr)
return None return None
self._db.close_session(sid) self._db.close_session(sid)
print(f'Capture stopped: session={sid} messages={self._msg_count} '
f'bytes={self._byte_count}', file=sys.stderr)
return sid return sid
def _capture_loop(self): def _capture_loop(self):
try:
for msg_type, data, flags in self._backend.iter_messages(): for msg_type, data, flags in self._backend.iter_messages():
if self._session_id is None: if self._session_id is None:
break break
try:
elapsed = round(time.monotonic() - self._start_time, 3) elapsed = round(time.monotonic() - self._start_time, 3)
mid = self._db.insert_message(self._session_id, elapsed, msg_type, data, flags) mid = self._db.insert_message(
self._session_id, elapsed, msg_type, data, flags)
self._msg_count += 1
self._byte_count += len(data)
self._latest_msg_id = mid self._latest_msg_id = mid
except Exception as e:
print(f'Capture: insert error, dropping msg: {e}',
file=sys.stderr)
continue
except Exception:
# The capture thread died unexpectedly (not a user stop).
sid = self._session_id
print(f'ERROR: capture thread stopped on error (session={sid}):',
file=sys.stderr)
traceback.print_exc()
self._stop_event.set()
if sid is not None:
try:
self._db.close_session(sid)
except Exception:
pass
self._session_id = None
return
def _log_loop(self):
while not self._stop_event.wait(self._log_interval):
if self._session_id is None:
break
dropped = getattr(self._backend, 'dropped', 0)
print(f'Capture alive: session={self._session_id} '
f'messages={self._msg_count} bytes={self._byte_count} '
f'dropped={dropped}', file=sys.stderr)
+133
View File
@@ -1,7 +1,10 @@
"""Tests for CaptureManager session lifecycle (empty-session discard).""" """Tests for CaptureManager session lifecycle (empty-session discard)."""
import contextlib
import io
import os import os
import tempfile import tempfile
import time
import unittest import unittest
from simtrace2_pysniff.server.capture import CaptureManager, gsmtap_msg_type from simtrace2_pysniff.server.capture import CaptureManager, gsmtap_msg_type
@@ -99,5 +102,135 @@ class TestCaptureManager(unittest.TestCase):
self.assertIsNone(mgr.device_connected) self.assertIsNone(mgr.device_connected)
class _FlakyReceiver:
"""Mimics GsmtapReceiver.read_packet, emitting scripted behaviors."""
def __init__(self, listener, behaviors):
self._listener = listener
self._behaviors = list(behaviors)
self._i = 0
def read_packet(self):
b = self._behaviors[self._i]
self._i += 1
if b == 'raise_non_sim':
raise ValueError('Not a GSMTAP SIM packet (type=99)')
if b == 'raise_short':
raise ValueError('GSMTAP packet too short: 3 bytes')
if b == 'none':
return None, None, 0
# 'good': return a valid APDU and terminate the loop.
self._listener._running = False
return 0x00, b'\x80\xf2\x00\x00\x00', 0
def close(self):
pass
class _NullDb:
def create_session(self, mode):
return 1
def count_messages(self, sid):
return 0
def delete_session(self, sid):
pass
def close_session(self, sid):
pass
def insert_message(self, *a, **k):
raise RuntimeError('db down')
class _OneShotBackend:
def start(self):
pass
def stop(self):
pass
def iter_messages(self):
yield ('tpdu', b'\x80\xf2\x00\x00\x00', 0)
class _RaisingBackend:
def start(self):
pass
def stop(self):
pass
def iter_messages(self):
raise RuntimeError('boom')
yield # unreachable
class TestGsmtapListenerRobustness(unittest.TestCase):
def test_listener_survives_bad_packet(self):
from simtrace2_pysniff.server.capture import GsmtapListener
listener = GsmtapListener(bind_port=0)
listener._receiver.close() # drop the real socket before swapping
listener._receiver = _FlakyReceiver(listener, ['raise_non_sim', 'good'])
listener.start()
out = list(listener.iter_messages())
listener.stop()
self.assertEqual(out, [('tpdu', b'\x80\xf2\x00\x00\x00', 0)])
self.assertEqual(listener.dropped, 1)
def test_listener_survives_short_packet(self):
from simtrace2_pysniff.server.capture import GsmtapListener
listener = GsmtapListener(bind_port=0)
listener._receiver.close() # drop the real socket before swapping
listener._receiver = _FlakyReceiver(listener, ['raise_short', 'good'])
listener.start()
out = list(listener.iter_messages())
listener.stop()
self.assertEqual(out, [('tpdu', b'\x80\xf2\x00\x00\x00', 0)])
self.assertEqual(listener.dropped, 1)
class TestCaptureLoopRobustness(unittest.TestCase):
def test_capture_loop_survives_insert_error(self):
mgr = CaptureManager(_OneShotBackend(), _NullDb())
mgr._session_id = 1
mgr._start_time = 0.0
# Must not raise; counters stay untouched on a dropped insert.
mgr._capture_loop()
self.assertEqual(mgr._session_id, 1)
self.assertEqual(mgr._msg_count, 0)
def test_capture_loop_logs_stop_on_error(self):
mgr = CaptureManager(_RaisingBackend(), _NullDb())
mgr._session_id = 7
mgr._start_time = 0.0
buf = io.StringIO()
with contextlib.redirect_stderr(buf):
mgr._capture_loop()
self.assertIn('stopped on error', buf.getvalue())
self.assertIsNone(mgr._session_id)
def test_capture_heartbeat_and_stop_log(self):
tmp = tempfile.NamedTemporaryFile(suffix='.db', delete=False)
tmp.close()
db = Database(tmp.name)
mgr = CaptureManager(_FakeBackend([('tpdu', b'\x80\xf2\x00\x00\x00', 0)]), db)
mgr._log_interval = 0.05
buf = io.StringIO()
with contextlib.redirect_stderr(buf):
mgr.start_session()
time.sleep(0.25)
mgr.stop_session()
log = buf.getvalue()
self.assertIn('Capture started', log)
self.assertIn('Capture alive', log)
self.assertIn('messages=1', log)
self.assertIn('bytes=5', log)
self.assertIn('Capture stopped', log)
db._conn.close()
os.remove(tmp.name)
if __name__ == '__main__': if __name__ == '__main__':
unittest.main() unittest.main()