Change trace to transport level

We may get multiple re-entries to debugger by `bp_forever` sub-actor
now since the root will incrementally try to cancel it only when the tty
lock is not held.

examples/debugging/fast_error_in_root_after_spawn.py

@@ -0,0 +1,53 @@
+'''
+fast fail test with a context.
+ensure the partially initialized sub-actor process
+doesn't cause a hang on error/cancel of the parent
+nrusery.
+
+'''
+import trio
+import tractor
+
+
+@tractor.context
+async def sleep(
+    ctx: tractor.Context,
+):
+    await trio.sleep(0.5)
+    await ctx.started()
+    await trio.sleep_forever()
+
+
+async def open_ctx(
+    n: tractor._trionics.ActorNursery
+):
+
+    # spawn both actors
+    portal = await n.start_actor(
+        name='sleeper',
+        enable_modules=[__name__],
+    )
+
+    async with portal.open_context(
+        sleep,
+    ) as (ctx, first):
+        assert first is None
+
+
+async def main():
+
+    async with tractor.open_nursery(
+        debug_mode=True,
+        loglevel='runtime',
+    ) as an:
+
+        async with trio.open_nursery() as n:
+            n.start_soon(open_ctx, an)
+
+            await trio.sleep(0.2)
+            await trio.sleep(0.1)
+            assert 0
+
+
+if __name__ == '__main__':
+    trio.run(main)

examples/debugging/root_timeout_while_child_crashed.py

@@ -0,0 +1,31 @@
+
+import trio
+import tractor
+
+
+async def key_error():
+    "Raise a ``NameError``"
+    return {}['doggy']
+
+
+async def main():
+    """Root dies 
+
+    """
+    async with tractor.open_nursery(
+        debug_mode=True,
+        loglevel='debug'
+    ) as n:
+
+        # spawn both actors
+        portal = await n.run_in_actor(key_error)
+
+        # XXX: originally a bug causes by this
+        # where root would enter debugger even
+        # though child should have it locked.
+        with trio.fail_after(1):
+            await trio.Event().wait()
+
+
+if __name__ == '__main__':
+    trio.run(main)

tests/test_debugger.py

@@ -317,32 +317,58 @@ def test_multi_daemon_subactors(spawn, loglevel):
         next_msg = name_error_msg
 
     elif name_error_msg in before:
-        next_msg = None
+        next_msg = bp_forever_msg
 
     else:
         raise ValueError("Neither log msg was found !?")
 
-    child.sendline('c')
+    # NOTE: previously since we did not have clobber prevention
+    # in the root actor this final resume could result in the debugger
+    # tearing down since both child actors would be cancelled and it was
+    # unlikely that `bp_forever` would re-acquire the tty loack again.
+    # Now, we should have a final resumption in the root plus a possible
+    # second entry by `bp_forever`.
 
-    # first name_error failure
+    child.sendline('c')
     child.expect(r"\(Pdb\+\+\)")
     before = str(child.before.decode())
 
-    if next_msg:
-        assert next_msg in before
+    assert next_msg in before
 
-    child.sendline('c')
+    # XXX: hoorayy the root clobering the child here was fixed!
+    # IMO, this demonstrates the true power of SC system design.
 
-    child.expect(r"\(Pdb\+\+\)")
-    before = str(child.before.decode())
-    assert "tractor._exceptions.RemoteActorError: ('name_error'" in before
+    # now the root actor won't clobber the bp_forever child
+    # during it's first access to the debug lock, but will instead
+    # wait for the lock to release, by the edge triggered
+    # ``_debug._no_remote_has_tty`` event before sending cancel messages
+    # (via portals) to its underlings B)
+
+    # at some point here there should have been some warning msg from
+    # the root announcing it avoided a clobber of the child's lock, but
+    # it seems unreliable in testing here to gnab it:
+    # assert "in use by child ('bp_forever'," in before
+
+    # wait for final error in root
+    while True:
+
+        child.sendline('c')
+        child.expect(r"\(Pdb\+\+\)")
+        before = str(child.before.decode())
+        try:
+
+            # root error should be packed as remote error
+            assert "_exceptions.RemoteActorError: ('name_error'" in before
+            break
+
+        except AssertionError:
+            assert bp_forever_msg in before
 
     try:
         child.sendline('c')
         child.expect(pexpect.EOF)
 
     except pexpect.exceptions.TIMEOUT:
-
         # Failed to exit using continue..?
         child.sendline('q')
         child.expect(pexpect.EOF)
@@ -397,7 +423,7 @@ def test_multi_nested_subactors_error_through_nurseries(spawn):
     child = spawn('multi_nested_subactors_error_up_through_nurseries')
 
     # startup time can be iffy
-    time.sleep(1)
+    # time.sleep(1)
 
     for i in range(12):
         try:
@@ -479,3 +505,21 @@ def test_root_nursery_cancels_before_child_releases_tty_lock(
         assert "tractor._exceptions.RemoteActorError: ('spawner0'" in before
         assert "tractor._exceptions.RemoteActorError: ('name_error'" in before
         assert "NameError: name 'doggypants' is not defined" in before
+
+
+def test_root_cancels_child_context_during_startup(
+    spawn,
+):
+    '''Verify a fast fail in the root doesn't lock up the child reaping
+    and all while using the new context api.
+
+    '''
+    child = spawn('fast_error_in_root_after_spawn')
+
+    child.expect(r"\(Pdb\+\+\)")
+
+    before = str(child.before.decode())
+    assert "AssertionError" in before
+
+    child.sendline('c')
+    child.expect(pexpect.EOF)

tractor/_actor.py

@@ -463,7 +463,8 @@ class Actor:
             log.runtime(
                 f"already have channel(s) for {uid}:{chans}?"
             )
-        log.trace(f"Registered {chan} for {uid}")  # type: ignore
+
+        log.runtime(f"Registered {chan} for {uid}")  # type: ignore
         # append new channel
         self._peers[uid].append(chan)
 
@@ -631,7 +632,7 @@ class Actor:
 
                         break
 
-                    log.trace(   # type: ignore
+                    log.transport(   # type: ignore
                         f"Received msg {msg} from {chan.uid}")
 
                     cid = msg.get('cid')

tractor/_debug.py

@@ -1,13 +1,13 @@
 """
 Multi-core debugging for da peeps!
+
 """
 import bdb
 import sys
 from functools import partial
 from contextlib import asynccontextmanager
-from typing import Awaitable, Tuple, Optional, Callable, AsyncIterator
+from typing import Tuple, Optional, Callable, AsyncIterator
 
-from async_generator import aclosing
 import tractor
 import trio
 
@@ -31,14 +31,22 @@ log = get_logger(__name__)
 
 __all__ = ['breakpoint', 'post_mortem']
 
+
+# TODO: wrap all these in a static global class: ``DebugLock`` maybe?
+
 # placeholder for function to set a ``trio.Event`` on debugger exit
 _pdb_release_hook: Optional[Callable] = None
 
 # actor-wide variable pointing to current task name using debugger
-_in_debug = False
+_local_task_in_debug: Optional[str] = None
+
+# actor tree-wide actor uid that supposedly has the tty lock
+_global_actor_in_debug: Optional[Tuple[str, str]] = None
 
 # lock in root actor preventing multi-access to local tty
-_debug_lock = trio.StrictFIFOLock()
+_debug_lock: trio.StrictFIFOLock = trio.StrictFIFOLock()
+_local_pdb_complete: Optional[trio.Event] = None
+_no_remote_has_tty: Optional[trio.Event] = None
 
 # XXX: set by the current task waiting on the root tty lock
 # and must be cancelled if this actor is cancelled via message
@@ -61,19 +69,19 @@ class PdbwTeardown(pdbpp.Pdb):
     # TODO: figure out how to dissallow recursive .set_trace() entry
     # since that'll cause deadlock for us.
     def set_continue(self):
-        global _in_debug
         try:
             super().set_continue()
         finally:
-            _in_debug = False
+            global _local_task_in_debug
+            _local_task_in_debug = None
             _pdb_release_hook()
 
     def set_quit(self):
-        global _in_debug
         try:
             super().set_quit()
         finally:
-            _in_debug = False
+            global _local_task_in_debug
+            _local_task_in_debug = None
             _pdb_release_hook()
 
 
@@ -102,7 +110,7 @@ class PdbwTeardown(pdbpp.Pdb):
 
 #     async with aclosing(async_stdin):
 #         async for msg in async_stdin:
-#             log.trace(f"Stdin input:\n{msg}")
+#             log.runtime(f"Stdin input:\n{msg}")
 #             # encode to bytes
 #             bmsg = str.encode(msg)
 
@@ -116,20 +124,71 @@ class PdbwTeardown(pdbpp.Pdb):
 
 @asynccontextmanager
 async def _acquire_debug_lock(uid: Tuple[str, str]) -> AsyncIterator[None]:
-    """Acquire a actor local FIFO lock meant to mutex entry to a local
-    debugger entry point to avoid tty clobbering by multiple processes.
-    """
+    '''Acquire a actor local FIFO lock meant to mutex entry to a local
+    debugger entry point to avoid tty clobbering a global root process.
+
+    '''
+    global _debug_lock, _global_actor_in_debug, _no_remote_has_tty
+
     task_name = trio.lowlevel.current_task().name
+
+    log.pdb(
+        f"Attempting to acquire TTY lock, remote task: {task_name}:{uid}"
+    )
+
+    we_acquired = False
+
+    if _no_remote_has_tty is None:
+        # mark the tty lock as being in use so that the runtime
+        # can try to avoid clobbering any connection from a child
+        # that's currently relying on it.
+        _no_remote_has_tty = trio.Event()
+
     try:
         log.debug(
-            f"Attempting to acquire TTY lock, remote task: {task_name}:{uid}")
+            f"entering lock checkpoint, remote task: {task_name}:{uid}"
+        )
+        we_acquired = True
         await _debug_lock.acquire()
 
+        # we_acquired = True
+
+        _global_actor_in_debug = uid
         log.debug(f"TTY lock acquired, remote task: {task_name}:{uid}")
-        yield
+
+        # NOTE: critical section!
+        # this yield is unshielded.
+        # IF we received a cancel during the shielded lock
+        # entry of some next-in-queue requesting task,
+        # then the resumption here will result in that
+        # Cancelled being raised to our caller below!
+
+        # in this case the finally below should trigger
+        # and the surrounding calle side context should cancel
+        # normally relaying back to the caller.
+
+        yield _debug_lock
 
     finally:
-        _debug_lock.release()
+        # if _global_actor_in_debug == uid:
+        if we_acquired and _debug_lock.locked():
+            _debug_lock.release()
+
+        # IFF there are no more requesting tasks queued up fire, the
+        # "tty-unlocked" event thereby alerting any monitors of the lock that
+        # we are now back in the "tty unlocked" state. This is basically
+        # and edge triggered signal around an empty queue of sub-actor
+        # tasks that may have tried to acquire the lock.
+        stats = _debug_lock.statistics()
+        if (
+            not stats.owner
+        ):
+            log.pdb(f"No more tasks waiting on tty lock! says {uid}")
+            _no_remote_has_tty.set()
+            _no_remote_has_tty = None
+
+        _global_actor_in_debug = None
+
         log.debug(f"TTY lock released, remote task: {task_name}:{uid}")
 
 
@@ -144,118 +203,200 @@ async def _acquire_debug_lock(uid: Tuple[str, str]) -> AsyncIterator[None]:
 #         signal.signal(signal.SIGINT, prior_handler)
 
 
+@tractor.context
 async def _hijack_stdin_relay_to_child(
+
+    ctx: tractor.Context,
     subactor_uid: Tuple[str, str]
-) -> AsyncIterator[str]:
+
+) -> str:
+    '''Hijack the tty in the root process of an actor tree such that
+    the pdbpp debugger console can be allocated to a sub-actor for repl
+    bossing.
+
+    '''
+    task_name = trio.lowlevel.current_task().name
+
     # TODO: when we get to true remote debugging
-    # this will deliver stdin data
-    log.warning(f"Actor {subactor_uid} is WAITING on stdin hijack lock")
-    async with _acquire_debug_lock(subactor_uid):
-        log.warning(f"Actor {subactor_uid} ACQUIRED stdin hijack lock")
+    # this will deliver stdin data?
 
-        # with _disable_sigint():
+    log.debug(
+        "Attempting to acquire TTY lock\n"
+        f"remote task: {task_name}:{subactor_uid}"
+    )
 
-        # indicate to child that we've locked stdio
-        yield 'Locked'
+    log.debug(f"Actor {subactor_uid} is WAITING on stdin hijack lock")
 
-        # wait for cancellation of stream by child
-        # indicating debugger is dis-engaged
-        await trio.sleep_forever()
+    with trio.CancelScope(shield=True):
 
-    log.debug(f"Actor {subactor_uid} RELEASED stdin hijack lock")
+        async with _acquire_debug_lock(subactor_uid):
+
+            # indicate to child that we've locked stdio
+            await ctx.started('Locked')
+            log.pdb(  # type: ignore
+                f"Actor {subactor_uid} ACQUIRED stdin hijack lock")
+
+            # wait for unlock pdb by child
+            async with ctx.open_stream() as stream:
+                try:
+                    assert await stream.receive() == 'pdb_unlock'
+
+                except trio.BrokenResourceError:
+                    # XXX: there may be a race with the portal teardown
+                    # with the calling actor which we can safely ignore
+                    # the alternative would be sending an ack message
+                    # and allowing the client to wait for us to teardown
+                    # first?
+                    pass
+
+    log.debug(
+        f"TTY lock released, remote task: {task_name}:{subactor_uid}")
+
+    return "pdb_unlock_complete"
 
 
-# XXX: We only make this sync in case someone wants to
-# overload the ``breakpoint()`` built-in.
-def _breakpoint(debug_func) -> Awaitable[None]:
+async def _breakpoint(debug_func) -> None:
     """``tractor`` breakpoint entry for engaging pdb machinery
     in subactors.
+
     """
     actor = tractor.current_actor()
-    do_unlock = trio.Event()
+    task_name = trio.lowlevel.current_task().name
+
+    global _local_pdb_complete, _pdb_release_hook
+    global _local_task_in_debug, _global_actor_in_debug
+
+    await trio.lowlevel.checkpoint()
 
     async def wait_for_parent_stdin_hijack(
         task_status=trio.TASK_STATUS_IGNORED
     ):
         global _debugger_request_cs
-        with trio.CancelScope() as cs:
+
+        with trio.CancelScope(shield=True) as cs:
             _debugger_request_cs = cs
+
             try:
                 async with get_root() as portal:
-                        async with portal.open_stream_from(
-                            tractor._debug._hijack_stdin_relay_to_child,
-                            subactor_uid=actor.uid,
-                        ) as stream:
 
-                                # block until first yield above
-                                async for val in stream:
+                    log.error('got portal')
 
-                                    assert val == 'Locked'
-                                    task_status.started()
+                    # this syncs to child's ``Context.started()`` call.
+                    async with portal.open_context(
 
-                                    # with trio.CancelScope(shield=True):
-                                    await do_unlock.wait()
+                        tractor._debug._hijack_stdin_relay_to_child,
+                        subactor_uid=actor.uid,
+
+                    ) as (ctx, val):
+
+                        log.error('locked context')
+                        assert val == 'Locked'
+
+                        async with ctx.open_stream() as stream:
+
+                            log.error('opened stream')
+                            # unblock local caller
+                            task_status.started()
+
+                            try:
+                                await _local_pdb_complete.wait()
+
+                            finally:
+                                # TODO: shielding currently can cause hangs...
+                                with trio.CancelScope(shield=True):
+                                    await stream.send('pdb_unlock')
+
+                            # sync with callee termination
+                            assert await ctx.result() == "pdb_unlock_complete"
+
+            except tractor.ContextCancelled:
+                log.warning('Root actor cancelled debug lock')
 
-                                    # trigger cancellation of remote stream
-                                    break
             finally:
                 log.debug(f"Exiting debugger for actor {actor}")
-                global _in_debug
-                _in_debug = False
+                global _local_task_in_debug
+                _local_task_in_debug = None
                 log.debug(f"Child {actor} released parent stdio lock")
 
-    async def _bp():
-        """Async breakpoint which schedules a parent stdio lock, and once complete
-        enters the ``pdbpp`` debugging console.
-        """
-        task_name = trio.lowlevel.current_task().name
+    if not _local_pdb_complete or _local_pdb_complete.is_set():
+        _local_pdb_complete = trio.Event()
 
-        global _in_debug
+    # TODO: need a more robust check for the "root" actor
+    if actor._parent_chan and not is_root_process():
 
-        # TODO: need a more robust check for the "root" actor
-        if actor._parent_chan and not is_root_process():
-            if _in_debug:
-                if _in_debug == task_name:
-                    # this task already has the lock and is
-                    # likely recurrently entering a breakpoint
-                    return
+        if _local_task_in_debug:
+            if _local_task_in_debug == task_name:
+                # this task already has the lock and is
+                # likely recurrently entering a breakpoint
+                return
 
-                # if **this** actor is already in debug mode block here
-                # waiting for the control to be released - this allows
-                # support for recursive entries to `tractor.breakpoint()`
-                log.warning(
-                    f"Actor {actor.uid} already has a debug lock, waiting...")
-                await do_unlock.wait()
-                await trio.sleep(0.1)
+            # if **this** actor is already in debug mode block here
+            # waiting for the control to be released - this allows
+            # support for recursive entries to `tractor.breakpoint()`
+            log.warning(f"{actor.uid} already has a debug lock, waiting...")
 
-            # assign unlock callback for debugger teardown hooks
-            global _pdb_release_hook
-            _pdb_release_hook = do_unlock.set
+            await _local_pdb_complete.wait()
+            await trio.sleep(0.1)
 
-            # mark local actor as "in debug mode" to avoid recurrent
-            # entries/requests to the root process
-            _in_debug = task_name
+        # mark local actor as "in debug mode" to avoid recurrent
+        # entries/requests to the root process
+        _local_task_in_debug = task_name
 
-            # this **must** be awaited by the caller and is done using the
-            # root nursery so that the debugger can continue to run without
-            # being restricted by the scope of a new task nursery.
+        # assign unlock callback for debugger teardown hooks
+        _pdb_release_hook = _local_pdb_complete.set
+
+        # this **must** be awaited by the caller and is done using the
+        # root nursery so that the debugger can continue to run without
+        # being restricted by the scope of a new task nursery.
+
+        # NOTE: if we want to debug a trio.Cancelled triggered exception
+        # we have to figure out how to avoid having the service nursery
+        # cancel on this task start? I *think* this works below?
+        # actor._service_n.cancel_scope.shield = shield
+        with trio.CancelScope(shield=True):
             await actor._service_n.start(wait_for_parent_stdin_hijack)
 
-        elif is_root_process():
-            # we also wait in the root-parent for any child that
-            # may have the tty locked prior
-            if _debug_lock.locked():  # root process already has it; ignore
-                return
-            await _debug_lock.acquire()
-            _pdb_release_hook = _debug_lock.release
+    elif is_root_process():
 
-        # block here one (at the appropriate frame *up* where
-        # ``breakpoint()`` was awaited and begin handling stdio
-        log.debug("Entering the synchronous world of pdb")
-        debug_func(actor)
+        # we also wait in the root-parent for any child that
+        # may have the tty locked prior
+        global _debug_lock
 
-    # user code **must** await this!
-    return _bp()
+        # TODO: wait, what about multiple root tasks acquiring
+        # it though.. shrug?
+        # root process (us) already has it; ignore
+        if _global_actor_in_debug == actor.uid:
+            return
+
+        # XXX: since we need to enter pdb synchronously below,
+        # we have to release the lock manually from pdb completion
+        # callbacks. Can't think of a nicer way then this atm.
+        if _debug_lock.locked():
+            log.warning(
+                'Root actor attempting to acquire active tty lock'
+                f' owned by {_global_actor_in_debug}')
+
+        await _debug_lock.acquire()
+
+        _global_actor_in_debug = actor.uid
+        _local_task_in_debug = task_name
+
+        # the lock must be released on pdb completion
+        def teardown():
+            global _local_pdb_complete, _debug_lock
+            global _global_actor_in_debug, _local_task_in_debug
+
+            _debug_lock.release()
+            _global_actor_in_debug = None
+            _local_task_in_debug = None
+            _local_pdb_complete.set()
+
+        _pdb_release_hook = teardown
+
+    # block here one (at the appropriate frame *up* where
+    # ``breakpoint()`` was awaited and begin handling stdio
+    log.debug("Entering the synchronous world of pdb")
+    debug_func(actor)
 
 
 def _mk_pdb():
@@ -276,7 +417,7 @@ def _set_trace(actor=None):
     pdb = _mk_pdb()
 
     if actor is not None:
-        log.runtime(f"\nAttaching pdb to actor: {actor.uid}\n")
+        log.pdb(f"\nAttaching pdb to actor: {actor.uid}\n")  # type: ignore
 
         pdb.set_trace(
             # start 2 levels up in user code
@@ -285,8 +426,8 @@ def _set_trace(actor=None):
 
     else:
         # we entered the global ``breakpoint()`` built-in from sync code
-        global _in_debug, _pdb_release_hook
-        _in_debug = 'sync'
+        global _local_task_in_debug, _pdb_release_hook
+        _local_task_in_debug = 'sync'
 
         def nuttin():
             pass
@@ -306,7 +447,7 @@ breakpoint = partial(
 
 
 def _post_mortem(actor):
-    log.runtime(f"\nAttaching to pdb in crashed actor: {actor.uid}\n")
+    log.pdb(f"\nAttaching to pdb in crashed actor: {actor.uid}\n")
     pdb = _mk_pdb()
 
     # custom Pdb post-mortem entry

tractor/_ipc.py

@@ -1,5 +1,6 @@
 """
 Inter-process comms abstractions
+
 """
 import platform
 import typing
@@ -61,7 +62,6 @@ class MsgpackTCPStream:
             use_list=False,
         )
         while True:
-
             try:
                 data = await self.stream.receive_some(2**10)
 
@@ -88,7 +88,7 @@ class MsgpackTCPStream:
                 else:
                     raise
 
-            log.trace(f"received {data}")  # type: ignore
+            log.transport(f"received {data}")  # type: ignore
 
             if data == b'':
                 raise TransportClosed(
@@ -169,6 +169,7 @@ class Channel:
         return self.msgstream.raddr if self.msgstream else None
 
     async def connect(
+
         self,
         destaddr: Tuple[Any, ...] = None,
         **kwargs
@@ -180,13 +181,21 @@ class Channel:
 
         destaddr = destaddr or self._destaddr
         assert isinstance(destaddr, tuple)
-        stream = await trio.open_tcp_stream(*destaddr, **kwargs)
+
+        stream = await trio.open_tcp_stream(
+            *destaddr,
+            **kwargs
+        )
         self.msgstream = MsgpackTCPStream(stream)
+
+        log.transport(
+            f'Opened channel to peer {self.laddr} -> {self.raddr}'
+        )
         return stream
 
     async def send(self, item: Any) -> None:
 
-        log.trace(f"send `{item}`")  # type: ignore
+        log.transport(f"send `{item}`")  # type: ignore
         assert self.msgstream
 
         await self.msgstream.send(item)
@@ -205,7 +214,8 @@ class Channel:
             raise
 
     async def aclose(self) -> None:
-        log.debug(
+
+        log.transport(
             f'Closing channel to {self.uid} '
             f'{self.laddr} -> {self.raddr}'
         )
@@ -234,11 +244,11 @@ class Channel:
                     await self.connect()
                 cancelled = cancel_scope.cancelled_caught
                 if cancelled:
-                    log.warning(
+                    log.transport(
                         "Reconnect timed out after 3 seconds, retrying...")
                     continue
                 else:
-                    log.warning("Stream connection re-established!")
+                    log.transport("Stream connection re-established!")
                     # run any reconnection sequence
                     on_recon = self._recon_seq
                     if on_recon:
@@ -247,7 +257,7 @@ class Channel:
             except (OSError, ConnectionRefusedError):
                 if not down:
                     down = True
-                    log.warning(
+                    log.transport(
                         f"Connection to {self.raddr} went down, waiting"
                         " for re-establishment")
                 await trio.sleep(1)

tractor/_root.py

@@ -171,8 +171,11 @@ async def open_root_actor(
                 yield actor
 
             except (Exception, trio.MultiError) as err:
-                logger.exception("Actor crashed:")
-                await _debug._maybe_enter_pm(err)
+                # with trio.CancelScope(shield=True):
+                entered = await _debug._maybe_enter_pm(err)
+
+                if not entered:
+                    logger.exception("Root actor crashed:")
 
                 # always re-raise
                 raise

tractor/_spawn.py

@@ -25,7 +25,11 @@ from . import _forkserver_override
 from ._state import (
     current_actor,
     is_main_process,
+    is_root_process,
+    _runtime_vars,
 )
+from ._debug import _global_actor_in_debug
+
 from .log import get_logger
 from ._portal import Portal
 from ._actor import Actor, ActorFailure
@@ -151,6 +155,27 @@ async def cancel_on_completion(
         # cancel the process now that we have a final result
         await portal.cancel_actor()
 
+async def do_hard_kill(
+    proc: trio.Process,
+
+) -> None:
+    # NOTE: this timeout used to do nothing since we were shielding
+    # the ``.wait()`` inside ``new_proc()`` which will pretty much
+    # never release until the process exits, now it acts as
+    # a hard-kill time ultimatum.
+    with trio.move_on_after(3) as cs:
+
+        # NOTE: This ``__aexit__()`` shields internally.
+        async with proc:  # calls ``trio.Process.aclose()``
+            log.debug(f"Terminating {proc}")
+
+    if cs.cancelled_caught:
+        # XXX: should pretty much never get here unless we have
+        # to move the bits from ``proc.__aexit__()`` out and
+        # into here.
+        log.critical(f"HARD KILLING {proc}")
+        proc.kill()
+
 
 async def do_hard_kill(
     proc: trio.Process,
@@ -206,12 +231,45 @@ async def spawn_subactor(
         yield proc
 
     finally:
+        log.runtime(f"Attempting to kill {proc}")
 
         # XXX: do this **after** cancellation/tearfown
         # to avoid killing the process too early
         # since trio does this internally on ``__aexit__()``
 
-        log.debug(f"Attempting to kill {proc}")
+        # if (
+        #     is_root_process()
+
+        #     # XXX: basically the pre-closing of stdstreams in a
+        #     # root-processe's ``trio.Process.aclose()`` can clobber
+        #     # any existing debugger session so we avoid
+        #     and _runtime_vars['_debug_mode']
+        #     and _global_actor_in_debug is not None
+        # ):
+        #     # XXX: this is ``trio.Process.aclose()`` MINUS the
+        #     # std-streams pre-closing steps inside ``proc.__aexit__()``
+        #     # (see below) which incluses a ``Process.kill()`` call
+
+        #     log.error(
+        #         "Root process tty is locked in debug mode by "
+        #         f"{_global_actor_in_debug}. If the console is hanging, you "
+        #         "may need to trigger a KBI to kill any "
+        #         "not-fully-initialized" " subprocesses and allow errors "
+        #         "from `trio` to propagate"
+        #     )
+        #     try:
+        #         # one more graceful wait try can can be cancelled by KBI
+        #         # sent by user.
+        #         await proc.wait()
+
+        #     finally:
+        #         if proc.returncode is None:
+        #             # with trio.CancelScope(shield=True):
+        #             #     await proc.wait()
+
+        #             await do_hard_kill(proc)
+        # else:
+
         await do_hard_kill(proc)
 
 

tractor/_trionics.py

@@ -11,7 +11,8 @@ import warnings
 import trio
 from async_generator import asynccontextmanager
 
-from ._state import current_actor, is_main_process
+from . import _debug
+from ._state import current_actor, is_main_process, is_root_process
 from .log import get_logger, get_loglevel
 from ._actor import Actor
 from ._portal import Portal
@@ -169,16 +170,25 @@ class ActorNursery:
 
         log.warning(f"Cancelling nursery in {self._actor.uid}")
         with trio.move_on_after(3) as cs:
+
             async with trio.open_nursery() as nursery:
+
                 for subactor, proc, portal in self._children.values():
+
+                    # TODO: are we ever even going to use this or
+                    # is the spawning backend responsible for such
+                    # things? I'm thinking latter.
                     if hard_kill:
                         proc.terminate()
+
                     else:
                         if portal is None:  # actor hasn't fully spawned yet
                             event = self._actor._peer_connected[subactor.uid]
                             log.warning(
                                 f"{subactor.uid} wasn't finished spawning?")
+
                             await event.wait()
+
                             # channel/portal should now be up
                             _, _, portal = self._children[subactor.uid]
 
@@ -238,6 +248,7 @@ async def _open_and_supervise_one_cancels_all_nursery(
             # As such if the strategy propagates any error(s) upwards
             # the above "daemon actor" nursery will be notified.
             async with trio.open_nursery() as ria_nursery:
+
                 anursery = ActorNursery(
                     actor,
                     ria_nursery,
@@ -248,21 +259,53 @@ async def _open_and_supervise_one_cancels_all_nursery(
                     # spawning of actors happens in the caller's scope
                     # after we yield upwards
                     yield anursery
-                    log.debug(
+
+                    log.runtime(
                         f"Waiting on subactors {anursery._children} "
                         "to complete"
                     )
 
                     # Last bit before first nursery block ends in the case
                     # where we didn't error in the caller's scope
-                    log.debug("Waiting on all subactors to complete")
+
+                    # signal all process monitor tasks to conduct
+                    # hard join phase.
                     anursery._join_procs.set()
 
                 except BaseException as err:
+
+                    # If we error in the root but the debugger is
+                    # engaged we don't want to prematurely kill (and
+                    # thus clobber access to) the local tty since it
+                    # will make the pdb repl unusable.
+                    # Instead try to wait for pdb to be released before
+                    # tearing down.
+                    if is_root_process():
+                        log.exception(f"we're root with {err}")
+
+                        # wait to see if a sub-actor task
+                        # will be scheduled and grab the tty
+                        # lock on the next tick
+                        # await trio.testing.wait_all_tasks_blocked()
+
+                        debug_complete = _debug._no_remote_has_tty
+                        if (
+                            debug_complete and
+                            not debug_complete.is_set()
+                        ):
+                            log.warning(
+                                'Root has errored but pdb is in use by '
+                                f'child {_debug._global_actor_in_debug}\n'
+                                'Waiting on tty lock to release..')
+
+                            with trio.CancelScope(shield=True):
+                                await debug_complete.wait()
+
                     # if the caller's scope errored then we activate our
                     # one-cancels-all supervisor strategy (don't
                     # worry more are coming).
                     anursery._join_procs.set()
+
                     try:
                         # XXX: hypothetically an error could be
                         # raised and then a cancel signal shows up
@@ -301,7 +344,15 @@ async def _open_and_supervise_one_cancels_all_nursery(
                 # ria_nursery scope end
 
         # XXX: do we need a `trio.Cancelled` catch here as well?
-        except (Exception, trio.MultiError, trio.Cancelled) as err:
+        # this is the catch around the ``.run_in_actor()`` nursery
+        except (
+
+            Exception,
+            trio.MultiError,
+            trio.Cancelled
+
+        ) as err:
+
             # If actor-local error was raised while waiting on
             # ".run_in_actor()" actors then we also want to cancel all
             # remaining sub-actors (due to our lone strategy:
@@ -368,6 +419,7 @@ async def open_nursery(
             async with open_root_actor(**kwargs) as actor:
                 assert actor is current_actor()
 
+                # try:
                 async with _open_and_supervise_one_cancels_all_nursery(
                     actor
                 ) as anursery:

tractor/log.py

@@ -29,19 +29,20 @@ LOG_FORMAT = (
 DATE_FORMAT = '%b %d %H:%M:%S'
 LEVELS = {
     'GARBAGE': 1,
-    'TRACE': 5,
-    'PROFILE': 15,
-    'RUNTIME': 500,
+    'TRANSPORT': 5,
+    'RUNTIME': 15,
+    'PDB': 500,
     'QUIET': 1000,
 }
 STD_PALETTE = {
     'CRITICAL': 'red',
     'ERROR': 'red',
-    'RUNTIME': 'white',
+    'PDB': 'white',
     'WARNING': 'yellow',
     'INFO': 'green',
+    'RUNTIME': 'white',
     'DEBUG': 'white',
-    'TRACE': 'cyan',
+    'TRANSPORT': 'cyan',
     'GARBAGE': 'blue',
 }
 BOLD_PALETTE = {
@@ -76,7 +77,7 @@ def get_logger(
     # additional levels
     for name, val in LEVELS.items():
         logging.addLevelName(val, name)
-        # ex. create ``logger.trace()``
+        # ex. create ``logger.runtime()``
         setattr(logger, name.lower(), partial(logger.log, val))
 
     return logger