Merge pull request #358 from goodboy/switch_to_pdbp

Switch to `pdbp` 🏄🏼

docs/README.rst

@@ -6,8 +6,14 @@
 ``tractor`` is a `structured concurrent`_, multi-processing_ runtime
 built on trio_.
 
-Fundamentally ``tractor`` gives you parallelism via ``trio``-"*actors*":
+Fundamentally, ``tractor`` gives you parallelism via
-our nurseries_ let you spawn new Python processes which each run a ``trio``
+``trio``-"*actors*": independent Python processes (aka
+non-shared-memory threads) which maintain structured
+concurrency (SC) *end-to-end* inside a *supervision tree*.
+
+Cross-process (and thus cross-host) SC is accomplished through the
+combined use of our "actor nurseries_" and an "SC-transitive IPC
+protocol" constructed on top of multiple Pythons each running a ``trio``
 scheduled runtime - a call to ``trio.run()``.
 
 We believe the system adheres to the `3 axioms`_ of an "`actor model`_"
@@ -23,7 +29,8 @@ Features
 - **It's just** a ``trio`` API
 - *Infinitely nesteable* process trees
 - Builtin IPC streaming APIs with task fan-out broadcasting
-- A (first ever?) "native" multi-core debugger UX for Python using `pdb++`_
+- A "native" multi-core debugger REPL using `pdbp`_ (a fork & fix of
+  `pdb++`_ thanks to @mdmintz!)
 - Support for a swappable, OS specific, process spawning layer
 - A modular transport stack, allowing for custom serialization (eg. with
   `msgspec`_), communications protocols, and environment specific IPC
@@ -149,7 +156,7 @@ it **is a bug**.
 
 "Native" multi-process debugging
 --------------------------------
-Using the magic of `pdb++`_ and our internal IPC, we've
+Using the magic of `pdbp`_ and our internal IPC, we've
 been able to create a native feeling debugging experience for
 any (sub-)process in your ``tractor`` tree.
 
@@ -597,6 +604,7 @@ channel`_!
 .. _adherance to: https://www.youtube.com/watch?v=7erJ1DV_Tlo&t=1821s
 .. _trio gitter channel: https://gitter.im/python-trio/general
 .. _matrix channel: https://matrix.to/#/!tractor:matrix.org
+.. _pdbp: https://github.com/mdmintz/pdbp
 .. _pdb++: https://github.com/pdbpp/pdbpp
 .. _guest mode: https://trio.readthedocs.io/en/stable/reference-lowlevel.html?highlight=guest%20mode#using-guest-mode-to-run-trio-on-top-of-other-event-loops
 .. _messages: https://en.wikipedia.org/wiki/Message_passing

examples/debugging/restore_builtin_breakpoint.py

@@ -0,0 +1,24 @@
+import os
+import sys
+
+import trio
+import tractor
+
+
+async def main() -> None:
+    async with tractor.open_nursery(debug_mode=True) as an:
+
+        assert os.environ['PYTHONBREAKPOINT'] == 'tractor._debug._set_trace'
+
+        # TODO: an assert that verifies the hook has indeed been, hooked
+        # XD
+        assert sys.breakpointhook is not tractor._debug._set_trace
+
+        breakpoint()
+
+    # TODO: an assert that verifies the hook is unhooked..
+    assert sys.breakpointhook
+    breakpoint()
+
+if __name__ == '__main__':
+    trio.run(main)

nooz/356.trivial.rst

@@ -0,0 +1,7 @@
+Drop `trio.Process.aclose()` usage, copy into our spawning code.
+
+The details are laid out in https://github.com/goodboy/tractor/issues/330.
+`trio` changed is process running quite some time ago, this just copies
+out the small bit we needed (from the old `.aclose()`) for hard kills
+where a soft runtime cancel request fails and our "zombie killer"
+implementation kicks in.

nooz/358.feature.rst

@@ -0,0 +1,15 @@
+Switch to using the fork & fix of `pdb++`, `pdbp`:
+https://github.com/mdmintz/pdbp
+
+Allows us to sidestep a variety of issues that aren't being maintained
+in the upstream project thanks to the hard work of @mdmintz!
+
+We also include some default settings adjustments as per recent
+development on the fork:
+
+- sticky mode is still turned on by default but now activates when
+  a using the `ll` repl command.
+- turn off line truncation by default to avoid inter-line gaps when
+  resizing the terimnal during use.
+- when using the backtrace cmd either by `w` or `bt`, the config
+  automatically switches to non-sticky mode.

requirements-test.txt

@@ -1,7 +1,7 @@
 pytest
 pytest-trio
 pytest-timeout
-pdbpp
+pdbp
 mypy
 trio_typing
 pexpect

tests/test_debugger.py

@@ -151,19 +151,6 @@ def ctlc(
 
     use_ctlc = request.param
 
-    # TODO: we can remove this bc pdbp right?
-    if (
-        sys.version_info <= (3, 10)
-        and use_ctlc
-    ):
-        # on 3.9 it seems the REPL UX
-        # is highly unreliable and frankly annoying
-        # to test for. It does work from manual testing
-        # but i just don't think it's wroth it to try
-        # and get this working especially since we want to
-        # be 3.10+ mega-asap.
-        pytest.skip('Py3.9 and `pdbpp` son no bueno..')
-
     node = request.node
     markers = node.own_markers
     for mark in markers:
@@ -194,13 +181,15 @@ def ctlc(
     ids=lambda item: f'{item[0]} -> {item[1]}',
 )
 def test_root_actor_error(spawn, user_in_out):
-    """Demonstrate crash handler entering pdbpp from basic error in root actor.
+    '''
-    """
+    Demonstrate crash handler entering pdb from basic error in root actor.
+
+    '''
     user_input, expect_err_str = user_in_out
 
     child = spawn('root_actor_error')
 
-    # scan for the pdbpp prompt
+    # scan for the prompt
     expect(child, PROMPT)
 
     before = str(child.before.decode())
@@ -231,7 +220,7 @@ def test_root_actor_bp(spawn, user_in_out):
     user_input, expect_err_str = user_in_out
     child = spawn('root_actor_breakpoint')
 
-    # scan for the pdbpp prompt
+    # scan for the prompt
     child.expect(PROMPT)
 
     assert 'Error' not in str(child.before)
@@ -339,7 +328,7 @@ def test_subactor_error(
     '''
     child = spawn('subactor_error')
 
-    # scan for the pdbpp prompt
+    # scan for the prompt
     child.expect(PROMPT)
 
     before = str(child.before.decode())
@@ -387,7 +376,7 @@ def test_subactor_breakpoint(
 
     child = spawn('subactor_breakpoint')
 
-    # scan for the pdbpp prompt
+    # scan for the prompt
     child.expect(PROMPT)
 
     before = str(child.before.decode())
@@ -448,7 +437,7 @@ def test_multi_subactors(
     '''
     child = spawn(r'multi_subactors')
 
-    # scan for the pdbpp prompt
+    # scan for the prompt
     child.expect(PROMPT)
 
     before = str(child.before.decode())
@@ -688,7 +677,7 @@ def test_multi_subactors_root_errors(
     '''
     child = spawn('multi_subactor_root_errors')
 
-    # scan for the pdbpp prompt
+    # scan for the prompt
     child.expect(PROMPT)
 
     # at most one subactor should attach before the root is cancelled

tractor/_debug.py

@@ -54,18 +54,6 @@ from ._exceptions import (
 )
 from ._ipc import Channel
 
-
-# TODO: we can drop this now yah?
-# try:
-#     # wtf: only exported when installed in dev mode?
-#     import pdbp
-# except ImportError:
-#     # pdbpp is installed in regular mode...it monkey patches stuff
-#     import pdb
-#     xpm = getattr(pdb, 'xpm', None)
-#     assert xpm, "pdbpp is not installed?"  # type: ignore
-#     pdbpp = pdb
-
 log = get_logger(__name__)
 
 
@@ -754,8 +742,8 @@ def shield_sigint_handler(
 
 
 def _set_trace(
-    actor: Optional[tractor.Actor] = None,
+    actor: tractor.Actor | None = None,
-    pdb: Optional[MultiActorPdb] = None,
+    pdb: MultiActorPdb | None = None,
 ):
     __tracebackhide__ = True
     actor = actor or tractor.current_actor()
@@ -765,7 +753,11 @@ def _set_trace(
     if frame:
         frame = frame.f_back  # type: ignore
 
-    if frame and pdb and actor is not None:
+    if (
+        frame
+        and pdb
+        and actor is not None
+    ):
         log.pdb(f"\nAttaching pdb to actor: {actor.uid}\n")
         # no f!#$&* idea, but when we're in async land
         # we need 2x frames up?
@@ -774,7 +766,8 @@ def _set_trace(
     else:
         pdb, undo_sigint = mk_mpdb()
 
-        # we entered the global ``breakpoint()`` built-in from sync code?
+        # we entered the global ``breakpoint()`` built-in from sync
+        # code?
         Lock.local_task_in_debug = 'sync'
 
     pdb.set_trace(frame=frame)

tractor/_root.py

@@ -22,8 +22,9 @@ from contextlib import asynccontextmanager
 from functools import partial
 import importlib
 import logging
-import os
 import signal
+import sys
+import os
 import typing
 import warnings
 
@@ -84,8 +85,10 @@ async def open_root_actor(
 
     '''
     # Override the global debugger hook to make it play nice with
-    # ``trio``, see:
+    # ``trio``, see much discussion in:
     # https://github.com/python-trio/trio/issues/1155#issuecomment-742964018
+    builtin_bp_handler = sys.breakpointhook
+    orig_bp_path: str | None = os.environ.get('PYTHONBREAKPOINT', None)
     os.environ['PYTHONBREAKPOINT'] = 'tractor._debug._set_trace'
 
     # attempt to retreive ``trio``'s sigint handler and stash it
@@ -254,6 +257,15 @@ async def open_root_actor(
                 await actor.cancel()
     finally:
         _state._current_actor = None
+
+        # restore breakpoint hook state
+        sys.breakpointhook = builtin_bp_handler
+        if orig_bp_path is not None:
+            os.environ['PYTHONBREAKPOINT'] = orig_bp_path
+        else:
+            # clear env back to having no entry
+            os.environ.pop('PYTHONBREAKPOINT')
+
         logger.runtime("Root actor terminated")
 
 
@@ -289,7 +301,7 @@ def run_daemon(
     async def _main():
 
         async with open_root_actor(
-            arbiter_addr=registry_addr,
+            registry_addr=registry_addr,
             name=name,
             start_method=start_method,
             debug_mode=debug_mode,

tractor/_spawn.py

@@ -23,13 +23,12 @@ import sys
 import platform
 from typing import (
     Any,
+    Awaitable,
     Literal,
-    Optional,
     Callable,
     TypeVar,
     TYPE_CHECKING,
 )
-from collections.abc import Awaitable
 
 from exceptiongroup import BaseExceptionGroup
 import trio
@@ -60,7 +59,7 @@ if TYPE_CHECKING:
 log = get_logger('tractor')
 
 # placeholder for an mp start context if so using that backend
-_ctx: Optional[mp.context.BaseContext] = None
+_ctx: mp.context.BaseContext | None = None
 SpawnMethodKey = Literal[
     'trio',  # supported on all platforms
     'mp_spawn',
@@ -86,7 +85,7 @@ else:
 def try_set_start_method(
     key: SpawnMethodKey
 
-) -> Optional[mp.context.BaseContext]:
+) -> mp.context.BaseContext | None:
     '''
     Attempt to set the method for process starting, aka the "actor
     spawning backend".
@@ -200,16 +199,37 @@ async def cancel_on_completion(
 async def do_hard_kill(
     proc: trio.Process,
     terminate_after: int = 3,
+
 ) -> 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.
+    log.debug(f"Terminating {proc}")
     with trio.move_on_after(terminate_after) as cs:
 
-        # NOTE: This ``__aexit__()`` shields internally.
+        # NOTE: code below was copied verbatim from the now deprecated
-        async with proc:  # calls ``trio.Process.aclose()``
+        # (in 0.20.0) ``trio._subrocess.Process.aclose()``, orig doc
-            log.debug(f"Terminating {proc}")
+        # string:
+        #
+        # Close any pipes we have to the process (both input and output)
+        # and wait for it to exit. If cancelled, kills the process and
+        # waits for it to finish exiting before propagating the
+        # cancellation.
+        with trio.CancelScope(shield=True):
+            if proc.stdin is not None:
+                await proc.stdin.aclose()
+            if proc.stdout is not None:
+                await proc.stdout.aclose()
+            if proc.stderr is not None:
+                await proc.stderr.aclose()
+        try:
+            await proc.wait()
+        finally:
+            if proc.returncode is None:
+                proc.kill()
+                with trio.CancelScope(shield=True):
+                    await proc.wait()
 
     if cs.cancelled_caught:
         # XXX: should pretty much never get here unless we have
@@ -355,12 +375,11 @@ async def trio_proc(
         spawn_cmd.append("--asyncio")
 
     cancelled_during_spawn: bool = False
-    proc: Optional[trio.Process] = None
+    proc: trio.Process | None = None
     try:
         try:
             # TODO: needs ``trio_typing`` patch?
-            proc = await trio.lowlevel.open_process(    # type: ignore
+            proc = await trio.lowlevel.open_process(spawn_cmd)
-                spawn_cmd)
 
             log.runtime(f"Started {proc}")
 
@@ -444,8 +463,8 @@ async def trio_proc(
             nursery.cancel_scope.cancel()
 
     finally:
-        # The "hard" reap since no actor zombies are allowed!
+        # XXX NOTE XXX: The "hard" reap since no actor zombies are
-        # XXX: do this **after** cancellation/tearfown to avoid
+        # allowed! Do this **after** cancellation/teardown to avoid
         # killing the process too early.
         if proc:
             log.cancel(f'Hard reap sequence starting for {subactor.uid}')