Merge pull request #165 from goodboy/signint_saviour

Ignore SIGINT when in a debugger REPL

.github/workflows/ci.yml

@@ -73,8 +73,11 @@ jobs:
       - name: Install dependencies
         run: pip install -U . -r requirements-test.txt -r requirements-docs.txt --upgrade-strategy eager
 
+      - name: List dependencies
+        run: pip freeze
+
       - name: Run tests
-        run: pytest tests/ --spawn-backend=${{ matrix.spawn_backend }} -rs
+        run: pytest tests/ --spawn-backend=${{ matrix.spawn_backend }} -rsx
 
   # We skip 3.10 on windows for now due to
   # https://github.com/pytest-dev/pytest/issues/8733
@@ -110,5 +113,8 @@ jobs:
       - name: Install dependencies
         run: pip install -U . -r requirements-test.txt -r requirements-docs.txt --upgrade-strategy eager
 
+      - name: List dependencies
+        run: pip freeze
+
       - name: Run tests
-        run: pytest tests/ --spawn-backend=${{ matrix.spawn_backend }} -rs
+        run: pytest tests/ --spawn-backend=${{ matrix.spawn_backend }} -rs --full-trace

docs/README.rst

@@ -3,13 +3,14 @@
 |gh_actions|
 |docs|
 
-``tractor`` is a `structured concurrent`_, multi-processing_ runtime built on trio_.
+``tractor`` is a `structured concurrent`_, multi-processing_ runtime
+built on trio_.
 
 Fundamentally ``tractor`` gives you parallelism via ``trio``-"*actors*":
 our nurseries_ let you spawn new Python processes which each run a ``trio``
 scheduled runtime - a call to ``trio.run()``.
 
-We believe the system adhere's to the `3 axioms`_ of an "`actor model`_"
+We believe the system adheres to the `3 axioms`_ of an "`actor model`_"
 but likely *does not* look like what *you* probably think an "actor
 model" looks like, and that's *intentional*.
 
@@ -577,13 +578,13 @@ say hi, please feel free to reach us in our `matrix channel`_.  If
 matrix seems too hip, we're also mostly all in the the `trio gitter
 channel`_!
 
+.. _structured concurrent: https://trio.discourse.group/t/concise-definition-of-structured-concurrency/228
+.. _multi-processing: https://en.wikipedia.org/wiki/Multiprocessing
+.. _trio: https://github.com/python-trio/trio
 .. _nurseries: https://vorpus.org/blog/notes-on-structured-concurrency-or-go-statement-considered-harmful/#nurseries-a-structured-replacement-for-go-statements
 .. _actor model: https://en.wikipedia.org/wiki/Actor_model
-.. _trio: https://github.com/python-trio/trio
-.. _multi-processing: https://en.wikipedia.org/wiki/Multiprocessing
 .. _trionic: https://trio.readthedocs.io/en/latest/design.html#high-level-design-principles
 .. _async sandwich: https://trio.readthedocs.io/en/latest/tutorial.html#async-sandwich
-.. _structured concurrent: https://trio.discourse.group/t/concise-definition-of-structured-concurrency/228
 .. _3 axioms: https://www.youtube.com/watch?v=7erJ1DV_Tlo&t=162s
 .. .. _3 axioms: https://en.wikipedia.org/wiki/Actor_model#Fundamental_concepts
 .. _adherance to: https://www.youtube.com/watch?v=7erJ1DV_Tlo&t=1821s

examples/debugging/open_ctx_modnofound.py

@@ -0,0 +1,40 @@
+import trio
+import tractor
+
+
+@tractor.context
+async def just_sleep(
+
+    ctx: tractor.Context,
+    **kwargs,
+
+) -> None:
+    '''
+    Start and sleep.
+
+    '''
+    await ctx.started()
+    await trio.sleep_forever()
+
+
+async def main() -> None:
+
+    async with tractor.open_nursery(
+        debug_mode=True,
+    ) as n:
+        portal = await n.start_actor(
+            'ctx_child',
+
+            # XXX: we don't enable the current module in order
+            # to trigger `ModuleNotFound`.
+            enable_modules=[],
+        )
+
+        async with portal.open_context(
+            just_sleep,  # taken from pytest parameterization
+        ) as (ctx, sent):
+            raise KeyboardInterrupt
+
+
+if __name__ == '__main__':
+    trio.run(main)

examples/debugging/subactor_bp_in_ctx.py

@@ -0,0 +1,50 @@
+import tractor
+import trio
+
+
+async def gen():
+    yield 'yo'
+    await tractor.breakpoint()
+    yield 'yo'
+    await tractor.breakpoint()
+
+
+@tractor.context
+async def just_bp(
+    ctx: tractor.Context,
+) -> None:
+
+    await ctx.started()
+    await tractor.breakpoint()
+
+    # TODO: bps and errors in this call..
+    async for val in gen():
+        print(val)
+
+    # await trio.sleep(0.5)
+
+    # prematurely destroy the connection
+    await ctx.chan.aclose()
+
+    # THIS CAUSES AN UNRECOVERABLE HANG
+    # without latest ``pdbpp``:
+    assert 0
+
+
+
+async def main():
+    async with tractor.open_nursery(
+        debug_mode=True,
+    ) as n:
+        p = await n.start_actor(
+            'bp_boi',
+            enable_modules=[__name__],
+        )
+        async with p.open_context(
+            just_bp,
+        ) as (ctx, first):
+            await trio.sleep_forever()
+
+
+if __name__ == '__main__':
+    trio.run(main)

examples/integration/open_context_and_sleep.py

@@ -0,0 +1,49 @@
+import trio
+import click
+import tractor
+import pydantic
+# from multiprocessing import shared_memory
+
+
+@tractor.context
+async def just_sleep(
+
+    ctx: tractor.Context,
+    **kwargs,
+
+) -> None:
+    '''
+    Test a small ping-pong 2-way streaming server.
+
+    '''
+    await ctx.started()
+    await trio.sleep_forever()
+
+
+async def main() -> None:
+
+    proc = await trio.open_process( (
+        'python',
+        '-c',
+        'import trio; trio.run(trio.sleep_forever)',
+    ))
+    await proc.wait()
+    # await trio.sleep_forever()
+    # async with tractor.open_nursery() as n:
+
+    #     portal = await n.start_actor(
+    #         'rpc_server',
+    #         enable_modules=[__name__],
+    #     )
+
+    #     async with portal.open_context(
+    #         just_sleep,  # taken from pytest parameterization
+    #     ) as (ctx, sent):
+    #         await trio.sleep_forever()
+
+
+
+if __name__ == '__main__':
+    import time
+    # time.sleep(999)
+    trio.run(main)

nooz/165.feature.rst

@@ -0,0 +1,36 @@
+Add SIGINT protection to our `pdbpp` based debugger subystem such that
+for (single-depth) actor trees in debug mode we ignore interrupts in any
+actor currently holding the TTY lock thus avoiding clobbering IPC
+connections and/or task and process state when working in the REPL.
+
+As a big note currently so called "nested" actor trees (trees with
+actors having more then one parent/ancestor) are not fully supported
+since we don't yet have a mechanism to relay the debug mode knowledge
+"up" the actor tree (for eg. when handling a crash in a leaf actor).
+As such currently there is a set of tests and known scenarios which will
+result in process cloberring by the zombie repaing machinery and these
+have been documented in https://github.com/goodboy/tractor/issues/320.
+
+The implementation details include:
+
+- utilizing a custom SIGINT handler which we apply whenever an actor's
+  runtime enters the debug machinery, which we also make sure the
+  stdlib's `pdb` configuration doesn't override (which it does by
+  default without special instance config).
+- litter the runtime with `maybe_wait_for_debugger()` mostly in spots
+  where the root actor should block before doing embedded nursery
+  teardown ops which both cancel potential-children-in-deubg as well
+  as eventually trigger zombie reaping machinery.
+- hardening of the TTY locking semantics/API both in terms of IPC
+  terminations and cancellation and lock release determinism from
+  sync debugger instance methods.
+- factoring of locking infrastructure into a new `._debug.Lock` global
+  which encapsulates all details of the ``trio`` sync primitives and
+  task/actor uid management and tracking.
+
+We also add `ctrl-c` cases throughout the test suite though these are
+disabled for py3.9 (`pdbpp` UX differences that don't seem worth
+compensating for, especially since this will be our last 3.9 supported
+release) and there are a slew of marked cases that aren't expected to
+work in CI more generally (as mentioned in the "nested" tree note
+above) despite seemingly working  when run manually on linux.

requirements-test.txt

@@ -1,5 +1,6 @@
 pytest
 pytest-trio
+pytest-timeout
 pdbpp
 mypy<0.920
 trio_typing<0.7.0

setup.py

@@ -43,7 +43,7 @@
     install_requires=[
 
         # trio related
-        'trio>0.8',
+        'trio >= 0.20',
         'async_generator',
         'trio_typing',
 
@@ -54,12 +54,23 @@
         # tooling
         'colorlog',
         'wrapt',
-        'pdbpp',
+
+        # pip ref docs on these specs:
+        # https://pip.pypa.io/en/stable/reference/requirement-specifiers/#examples
+        # and pep:
+        # https://peps.python.org/pep-0440/#version-specifiers
+        'pdbpp <= 0.10.1; python_version < "3.10"',
+
         # windows deps workaround for ``pdbpp``
         # https://github.com/pdbpp/pdbpp/issues/498
         # https://github.com/pdbpp/fancycompleter/issues/37
         'pyreadline3 ; platform_system == "Windows"',
 
+        # 3.10 has an outstanding unreleased issue and `pdbpp` itself
+        #   pins to patched forks of its own dependencies as well..and
+        #   we need a specific patch on master atm.
+        'pdbpp @ git+https://github.com/pdbpp/pdbpp@76c4be5#egg=pdbpp ; python_version > "3.9"',  # noqa: E501
+
         # serialization
         'msgspec >= "0.4.0"'
 
@@ -83,8 +94,8 @@
         "License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)",
         "Programming Language :: Python :: Implementation :: CPython",
         "Programming Language :: Python :: 3 :: Only",
-        "Programming Language :: Python :: 3.10",
         "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
         "Intended Audience :: Science/Research",
         "Intended Audience :: Developers",
         "Topic :: System :: Distributed Computing",

tests/conftest.py

@@ -85,11 +85,14 @@ def spawn_backend(request):
     return request.config.option.spawn_backend
 
 
+_ci_env: bool = os.environ.get('CI', False)
+
+
 @pytest.fixture(scope='session')
 def ci_env() -> bool:
     """Detect CI envoirment.
     """
-    return os.environ.get('TRAVIS', False) or os.environ.get('CI', False)
+    return _ci_env
 
 
 @pytest.fixture(scope='session')

tests/test_context_stream_semantics.py

@@ -265,42 +265,44 @@ async def test_callee_closes_ctx_after_stream_open():
             enable_modules=[__name__],
         )
 
-        async with portal.open_context(
-            close_ctx_immediately,
+        with trio.fail_after(2):
+            async with portal.open_context(
+                close_ctx_immediately,
 
-            # flag to avoid waiting the final result
-            # cancel_on_exit=True,
+                # flag to avoid waiting the final result
+                # cancel_on_exit=True,
 
-        ) as (ctx, sent):
+            ) as (ctx, sent):
 
-            assert sent is None
+                assert sent is None
 
-            with trio.fail_after(0.5):
-                async with ctx.open_stream() as stream:
-
-                    # should fall through since ``StopAsyncIteration``
-                    # should be raised through translation of
-                    # a ``trio.EndOfChannel`` by
-                    # ``trio.abc.ReceiveChannel.__anext__()``
-                    async for _ in stream:
-                        assert 0
-                    else:
-
-                        # verify stream is now closed
-                        try:
-                            await stream.receive()
-                        except trio.EndOfChannel:
-                            pass
+                with trio.fail_after(0.5):
+                    async with ctx.open_stream() as stream:
 
-            # TODO: should be just raise the closed resource err
-            # directly here to enforce not allowing a re-open
-            # of a stream to the context (at least until a time of
-            # if/when we decide that's a good idea?)
-            try:
-                async with ctx.open_stream() as stream:
+                        # should fall through since ``StopAsyncIteration``
+                        # should be raised through translation of
+                        # a ``trio.EndOfChannel`` by
+                        # ``trio.abc.ReceiveChannel.__anext__()``
+                        async for _ in stream:
+                            assert 0
+                        else:
+
+                            # verify stream is now closed
+                            try:
+                                await stream.receive()
+                            except trio.EndOfChannel:
+                                pass
+
+                # TODO: should be just raise the closed resource err
+                # directly here to enforce not allowing a re-open
+                # of a stream to the context (at least until a time of
+                # if/when we decide that's a good idea?)
+                try:
+                    with trio.fail_after(0.5):
+                        async with ctx.open_stream() as stream:
+                            pass
+                except trio.ClosedResourceError:
                     pass
-            except trio.ClosedResourceError:
-                pass
 
         await portal.cancel_actor()