Skip to content

Commit

Permalink
Reentrant hacks.
Browse files Browse the repository at this point in the history
  • Loading branch information
perlow committed Jul 27, 2019
1 parent ef29dab commit b73a954
Show file tree
Hide file tree
Showing 4 changed files with 653 additions and 19 deletions.
1 change: 1 addition & 0 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -29,4 +29,5 @@ __pycache__/
docs/_build
uvloop/loop.*.pyd
/.pytest_cache/
uvloop-dev/

326 changes: 326 additions & 0 deletions uvloop/futures.pyx
Original file line number Diff line number Diff line change
@@ -0,0 +1,326 @@
__all__ = ['Future']

import sys
import traceback

from asyncio import base_futures
from asyncio import compat
from asyncio import events

CancelledError = base_futures.CancelledError
InvalidStateError = base_futures.InvalidStateError
TimeoutError = base_futures.TimeoutError

_PENDING = base_futures._PENDING
_CANCELLED = base_futures._CANCELLED
_FINISHED = base_futures._FINISHED

class _TracebackLogger:
"""Helper to log a traceback upon destruction if not cleared.
This solves a nasty problem with Futures and Tasks that have an
exception set: if nobody asks for the exception, the exception is
never logged. This violates the Zen of Python: 'Errors should
never pass silently. Unless explicitly silenced.'
However, we don't want to log the exception as soon as
set_exception() is called: if the calling code is written
properly, it will get the exception and handle it properly. But
we *do* want to log it if result() or exception() was never called
-- otherwise developers waste a lot of time wondering why their
buggy code fails silently.
An earlier attempt added a __del__() method to the Future class
itself, but this backfired because the presence of __del__()
prevents garbage collection from breaking cycles. A way out of
this catch-22 is to avoid having a __del__() method on the Future
class itself, but instead to have a reference to a helper object
with a __del__() method that logs the traceback, where we ensure
that the helper object doesn't participate in cycles, and only the
Future has a reference to it.
The helper object is added when set_exception() is called. When
the Future is collected, and the helper is present, the helper
object is also collected, and its __del__() method will log the
traceback. When the Future's result() or exception() method is
called (and a helper object is present), it removes the helper
object, after calling its clear() method to prevent it from
logging.
One downside is that we do a fair amount of work to extract the
traceback from the exception, even when it is never logged. It
would seem cheaper to just store the exception object, but that
references the traceback, which references stack frames, which may
reference the Future, which references the _TracebackLogger, and
then the _TracebackLogger would be included in a cycle, which is
what we're trying to avoid! As an optimization, we don't
immediately format the exception; we only do the work when
activate() is called, which call is delayed until after all the
Future's callbacks have run. Since usually a Future has at least
one callback (typically set by 'yield from') and usually that
callback extracts the callback, thereby removing the need to
format the exception.
PS. I don't claim credit for this solution. I first heard of it
in a discussion about closing files when they are collected.
"""

__slots__ = ('loop', 'source_traceback', 'exc', 'tb')

def __init__(self, future, exc):
self.loop = future._loop
self.source_traceback = future._source_traceback
self.exc = exc
self.tb = None

def activate(self):
exc = self.exc
if exc is not None:
self.exc = None
self.tb = traceback.format_exception(exc.__class__, exc,
exc.__traceback__)

def clear(self):
self.exc = None
self.tb = None

def __del__(self):
if self.tb:
msg = 'Future/Task exception was never retrieved\n'
if self.source_traceback:
src = ''.join(traceback.format_list(self.source_traceback))
msg += 'Future/Task created at (most recent call last):\n'
msg += '%s\n' % src.rstrip()
msg += ''.join(self.tb).rstrip()
self.loop.call_exception_handler({'message': msg})


cdef class Future:
"""This class is *almost* compatible with concurrent.futures.Future.
Differences:
- This class is not thread-safe.
- result() and exception() do not take a timeout argument and
raise an exception when the future isn't done yet.
- Callbacks registered with add_done_callback() are always called
via the event loop's call_soon().
- This class is not compatible with the wait() and as_completed()
methods in the concurrent.futures package.
(In Python 3.4 or later we may be able to unify the implementations.)
"""

cdef public str _state
cdef public object _result
cdef public Exception _exception
cdef public object _loop
cdef public object _source_traceback
cdef public list _callbacks

# This field is used for a dual purpose:
# - Its presence is a marker to declare that a class implements
# the Future protocol (i.e. is intended to be duck-type compatible).
# The value must also be not-None, to enable a subclass to declare
# that it is not compatible by setting this to None.
# - It is set by __iter__() below so that Task._step() can tell
# the difference between `yield from Future()` (correct) vs.
# `yield Future()` (incorrect).
cdef int _asyncio_future_blocking

cdef int _log_traceback

def __init__(self, *, loop=None):
"""Initialize the future.
The optional event_loop argument allows explicitly setting the event
loop object used by the future. If it's not provided, the future uses
the default event loop.
"""
self._state = _PENDING
self._result = None
self._exception = None
self._loop = None
self._source_traceback = None
if loop is None:
self._loop = events.get_event_loop()
else:
self._loop = loop
self._callbacks = []
if self._loop.get_debug():
self._source_traceback = events.extract_stack(sys._getframe(1))

_repr_info = base_futures._future_repr_info

def __repr__(self):
return '<%s %s>' % (self.__class__.__name__, ' '.join(self._repr_info()))

# On Python 3.3 and older, objects with a destructor part of a reference
# cycle are never destroyed. It's not more the case on Python 3.4 thanks
# to the PEP 442.
if compat.PY34:
def __del__(self):
if not self._log_traceback:
# set_exception() was not called, or result() or exception()
# has consumed the exception
return
exc = self._exception
context = {
'message': ('%s exception was never retrieved'
% self.__class__.__name__),
'exception': exc,
'future': self,
}
if self._source_traceback:
context['source_traceback'] = self._source_traceback
self._loop.call_exception_handler(context)

def cancel(self):
"""Cancel the future and schedule callbacks.
If the future is already done or cancelled, return False. Otherwise,
change the future's state to cancelled, schedule the callbacks and
return True.
"""
self._log_traceback = 0
if self._state != _PENDING:
return False
self._state = _CANCELLED
self._schedule_callbacks()
return True

def _schedule_callbacks(self):
"""Internal: Ask the event loop to call all callbacks.
The callbacks are scheduled to be called as soon as possible. Also
clears the callback list.
"""
callbacks = self._callbacks[:]
if not callbacks:
return

self._callbacks[:] = []
for callback in callbacks:
self._loop.call_soon(callback, self)

def cancelled(self):
"""Return True if the future was cancelled."""
return self._state == _CANCELLED

# Don't implement running(); see http://bugs.python.org/issue18699

def done(self):
"""Return True if the future is done.
Done means either that a result / exception are available, or that the
future was cancelled.
"""
return self._state != _PENDING

def result(self):
"""Return the result this future represents.
If the future has been cancelled, raises CancelledError. If the
future's result isn't yet available, raises InvalidStateError. If
the future is done and has an exception set, this exception is raised.
"""
if self._state == _CANCELLED:
raise CancelledError
if self._state != _FINISHED:
raise InvalidStateError('Result is not ready.')
self._log_traceback = 0
if self._exception is not None:
raise self._exception
return self._result

def exception(self):
"""Return the exception that was set on this future.
The exception (or None if no exception was set) is returned only if
the future is done. If the future has been cancelled, raises
CancelledError. If the future isn't done yet, raises
InvalidStateError.
"""
if self._state == _CANCELLED:
raise CancelledError
if self._state != _FINISHED:
raise InvalidStateError('Exception is not set.')
self._log_traceback = 0
return self._exception

def add_done_callback(self, fn):
"""Add a callback to be run when the future becomes done.
The callback is called with a single argument - the future object. If
the future is already done when this is called, the callback is
scheduled with call_soon.
"""
if self._state != _PENDING:
self._loop.call_soon(fn, self)
else:
self._callbacks.append(fn)

# New method not in PEP 3148.

def remove_done_callback(self, fn):
"""Remove all instances of a callback from the "call when done" list.
Returns the number of callbacks removed.
"""
filtered_callbacks = [f for f in self._callbacks if f != fn]
removed_count = len(self._callbacks) - len(filtered_callbacks)
if removed_count:
self._callbacks[:] = filtered_callbacks
return removed_count

# So-called internal methods (note: no set_running_or_notify_cancel()).

def set_result(self, result):
"""Mark the future done and set its result.
If the future is already done when this method is called, raises
InvalidStateError.
"""
if self._state != _PENDING:
raise InvalidStateError('{}: {!r}'.format(self._state, self))
self._result = result
self._state = _FINISHED
self._schedule_callbacks()

def set_exception(self, exception):
"""Mark the future done and set an exception.
If the future is already done when this method is called, raises
InvalidStateError.
"""
if self._state != _PENDING:
raise InvalidStateError('{}: {!r}'.format(self._state, self))
if isinstance(exception, type):
exception = exception()
if type(exception) is StopIteration:
raise TypeError("StopIteration interacts badly with generators "
"and cannot be raised into a Future")
self._exception = exception
self._state = _FINISHED
self._schedule_callbacks()
if compat.PY34:
self._log_traceback = 1
else:
self._tb_logger = _TracebackLogger(self, exception)
# Arrange for the logger to be activated after all callbacks
# have had a chance to call result() or exception().
self._loop.call_soon(self._tb_logger.activate)

def __iter__(self):
if not self.done():
self._asyncio_future_blocking = 1
yield self # This tells Task to wait for completion.
assert self.done(), "yield from wasn't used with future"
return self.result() # May raise too.

if compat.PY35:
__await__ = __iter__ # make compatible with 'await' expression

Loading

0 comments on commit b73a954

Please sign in to comment.