1. 用法注释
在解析之前，我们先介绍一下这个包里有些什么。
1.1 条件变量
# Consume one item
with cv:
while not an_item_is_available():
cv.wait()
get_an_available_item()
# Produce one item
with cv:
make_an_item_available()
cv.notify()
这段代码中基于with语句管理锁的获取和释放比较容易理解（可参考context manager protocol），关键是cv.wait()做了什么。这个简单的查阅库文档并不直观，我们可以参考Linux Programming Interface(第30章，2.2小节）一书中对于条件变量的阐述得到一些启发：
（1）线程在准备检查共享变量状态时锁定互斥量。
（2）检查共享变量的状态。
（3）如果共享变量未处于预期状态，线程应该在等待条件变量并进入休眠前解锁互斥量（以便其它线程能访问该共享变量）。
（4）当线程因为条件变量的通知而被再度唤醒时，必须对互斥量再次加锁，因为在典型情况下，线程会立即访问共享变量。
函数pthread_cond_wait()会自动执行最后两步中对互斥量的解锁和加锁动作。第三步中互斥量的释放与陷入对条件变量的等待同属一个原子操作。换句话说，在函数pthread_cond_wait()的调用线程陷入对条件变量的等待之前，其他线程不可能获取到该互斥量，也不可能就该条件变量发出信号。
1.2 信号量
一般用来对一些资源的数量做限制，比如数据库连接数，又比如线程池的线程数等，比如如下代码，限制多个线程至多只能创建5个到数据库的连接：
maxconnections = 5
# ...
pool_sema = BoundedSemaphore(value=maxconnections)
with pool_sema:
conn = connectdb()
try:
# ... use connection ...
finally:
conn.close()
1.3 Event
这个看着很奇怪，一个线程等待一个事件，另一个线程唤醒它，似乎用处不大。看了下源码，是条件变量实现的
class Event:
"""Class implementing event objects.
Events manage a flag that can be set to true with the set() method and reset
to false with the clear() method. The wait() method blocks until the flag is
true. The flag is initially false.
"""
# After Tim Peters' event class (without is_posted())
def __init__(self):
self._cond = Condition(Lock())
self._flag = False
def _reset_internal_locks(self):
# private! called by Thread._reset_internal_locks by _after_fork()
self._cond.__init__(Lock())
def is_set(self):
"""Return true if and only if the internal flag is true."""
return self._flag
isSet = is_set
def set(self):
"""Set the internal flag to true.
All threads waiting for it to become true are awakened. Threads
that call wait() once the flag is true will not block at all.
"""
with self._cond:
self._flag = True
self._cond.notify_all()
def clear(self):
"""Reset the internal flag to false.
Subsequently, threads calling wait() will block until set() is called to
set the internal flag to true again.
"""
with self._cond:
self._flag = False
def wait(self, timeout=None):
"""Block until the internal flag is true.
If the internal flag is true on entry, return immediately. Otherwise,
block until another thread calls set() to set the flag to true, or until
the optional timeout occurs.
When the timeout argument is present and not None, it should be a
floating point number specifying a timeout for the operation in seconds
(or fractions thereof).
This method returns the internal flag on exit, so it will always return
True except if a timeout is given and the operation times out.
"""
with self._cond:
signaled = self._flag
if not signaled:
signaled = self._cond.wait(timeout)
return signaled
1.4 Timer
定时执行某个函数，示例：
def hello():
print("hello, world")
t = Timer(30.0, hello)
t.start() # after 30 seconds, "hello, world" will be printed
从实现来看，就是wait函数timeout之后执行某段代码，看不出来有啥用
class Timer(Thread):
"""Call a function after a specified number of seconds:
t = Timer(30.0, f, args=None, kwargs=None)
t.start()
t.cancel() # stop the timer's action if it's still waiting
"""
def __init__(self, interval, function, args=None, kwargs=None):
Thread.__init__(self)
self.interval = interval
self.function = function
self.args = args if args is not None else []
self.kwargs = kwargs if kwargs is not None else {}
self.finished = Event()
def cancel(self):
"""Stop the timer if it hasn't finished yet."""
self.finished.set()
def run(self):
self.finished.wait(self.interval)
if not self.finished.is_set():
self.function(*self.args, **self.kwargs)
self.finished.set()
1.5 Barrier
使得所有线程都至少执行到某个地方再往下，示例:
b = Barrier(2, timeout=5)
def server():
start_server()
b.wait()
while True:
connection = accept_connection()
process_server_connection(connection)
def client():
b.wait()
while True:
connection = make_connection()
process_client_connection(connection)
class Barrier:
"""Implements a Barrier.
Useful for synchronizing a fixed number of threads at known synchronization
points. Threads block on 'wait()' and are simultaneously once they have all
made that call.
"""
def __init__(self, parties, action=None, timeout=None):
"""Create a barrier, initialised to 'parties' threads.
'action' is a callable which, when supplied, will be called by one of
the threads after they have all entered the barrier and just prior to
releasing them all. If a 'timeout' is provided, it is uses as the
default for all subsequent 'wait()' calls.
"""
self._cond = Condition(Lock())
self._action = action
self._timeout = timeout
self._parties = parties
self._state = 0 #0 filling, 1, draining, -1 resetting, -2 broken
self._count = 0
def wait(self, timeout=None):
"""Wait for the barrier.
When the specified number of threads have started waiting, they are all
simultaneously awoken. If an 'action' was provided for the barrier, one
of the threads will have executed that callback prior to returning.
Returns an individual index number from 0 to 'parties-1'.
"""
if timeout is None:
timeout = self._timeout
with self._cond:
self._enter() # Block while the barrier drains.
index = self._count
self._count += 1
try:
if index + 1 == self._parties:
# We release the barrier
self._release()
else:
# We wait until someone releases us
self._wait(timeout)
return index
finally:
self._count -= 1
# Wake up any threads waiting for barrier to drain.
self._exit()
# Block until the barrier is ready for us, or raise an exception
# if it is broken.
def _enter(self):
while self._state in (-1, 1):
# It is draining or resetting, wait until done
self._cond.wait()
#see if the barrier is in a broken state
if self._state < 0:
raise BrokenBarrierError
assert self._state == 0
# Optionally run the 'action' and release the threads waiting
# in the barrier.
def _release(self):
try:
if self._action:
self._action()
# enter draining state
self._state = 1
self._cond.notify_all()
except:
#an exception during the _action handler. Break and reraise
self._break()
raise
# Wait in the barrier until we are released. Raise an exception
# if the barrier is reset or broken.
def _wait(self, timeout):
if not self._cond.wait_for(lambda : self._state != 0, timeout):
#timed out. Break the barrier
self._break()
raise BrokenBarrierError
if self._state < 0:
raise BrokenBarrierError
assert self._state == 1
# If we are the last thread to exit the barrier, signal any threads
# waiting for the barrier to drain.
def _exit(self):
if self._count == 0:
if self._state in (-1, 1):
#resetting or draining
self._state = 0
self._cond.notify_all()
def reset(self):
"""Reset the barrier to the initial state.
Any threads currently waiting will get the BrokenBarrier exception
raised.
"""
with self._cond:
if self._count > 0:
if self._state == 0:
#reset the barrier, waking up threads
self._state = -1
elif self._state == -2:
#was broken, set it to reset state
#which clears when the last thread exits
self._state = -1
else:
self._state = 0
self._cond.notify_all()
def abort(self):
"""Place the barrier into a 'broken' state.
Useful in case of error. Any currently waiting threads and threads
attempting to 'wait()' will have BrokenBarrierError raised.
"""
with self._cond:
self._break()
def _break(self):
# An internal error was detected. The barrier is set to
# a broken state all parties awakened.
self._state = -2
self._cond.notify_all()
@property
def parties(self):
"""Return the number of threads required to trip the barrier."""
return self._parties
@property
def n_waiting(self):
"""Return the number of threads currently waiting at the barrier."""
# We don't need synchronization here since this is an ephemeral result
# anyway. It returns the correct value in the steady state.
if self._state == 0:
return self._count
return 0
@property
def broken(self):
"""Return True if the barrier is in a broken state."""
return self._state == -2
2. 实现解析
2.1ThreadPoolExecutor实现
class ThreadPoolExecutor(_base.Executor):
# Used to assign unique thread names when thread_name_prefix is not supplied.
_counter = itertools.count().__next__
def __init__(self, max_workers=None, thread_name_prefix='',
initializer=None, initargs=()):
"""Initializes a new ThreadPoolExecutor instance.
Args:
max_workers: The maximum number of threads that can be used to
execute the given calls.
thread_name_prefix: An optional name prefix to give our threads.
initializer: An callable used to initialize worker threads.
initargs: A tuple of arguments to pass to the initializer.
"""
if max_workers is None:
# Use this number because ThreadPoolExecutor is often
# used to overlap I/O instead of CPU work.
max_workers = (os.cpu_count() or 1) * 5
if max_workers <= 0:
raise ValueError("max_workers must be greater than 0")
if initializer is not None and not callable(initializer):
raise TypeError("initializer must be a callable")
self._max_workers = max_workers
self._work_queue = queue.SimpleQueue()
self._threads = set()
self._broken = False
self._shutdown = False
self._shutdown_lock = threading.Lock()
self._thread_name_prefix = (thread_name_prefix or
("ThreadPoolExecutor-%d" % self._counter()))
self._initializer = initializer
self._initargs = initargs
def submit(self, fn, *args, **kwargs):
with self._shutdown_lock:
if self._broken:
raise BrokenThreadPool(self._broken)
if self._shutdown:
raise RuntimeError('cannot schedule new futures after shutdown')
if _shutdown:
raise RuntimeError('cannot schedule new futures after'
'interpreter shutdown')
f = _base.Future()
w = _WorkItem(f, fn, args, kwargs)
self._work_queue.put(w)
self._adjust_thread_count()
return f
submit.__doc__ = _base.Executor.submit.__doc__
def _adjust_thread_count(self):
# When the executor gets lost, the weakref callback will wake up
# the worker threads.
def weakref_cb(_, q=self._work_queue):
q.put(None)
# TODO(bquinlan): Should avoid creating new threads if there are more
# idle threads than items in the work queue.
num_threads = len(self._threads)
if num_threads < self._max_workers:
thread_name = '%s_%d' % (self._thread_name_prefix or self,
num_threads)
t = threading.Thread(name=thread_name, target=_worker,
args=(weakref.ref(self, weakref_cb),
self._work_queue,
self._initializer,
self._initargs))
t.daemon = True
t.start()
self._threads.add(t)
_threads_queues[t] = self._work_queue
def _initializer_failed(self):
with self._shutdown_lock:
self._broken = ('A thread initializer failed, the thread pool '
'is not usable anymore')
# Drain work queue and mark pending futures failed
while True:
try:
work_item = self._work_queue.get_nowait()
except queue.Empty:
break
if work_item is not None:
work_item.future.set_exception(BrokenThreadPool(self._broken))
def shutdown(self, wait=True):
with self._shutdown_lock:
self._shutdown = True
self._work_queue.put(None)
if wait:
for t in self._threads:
t.join()
shutdown.__doc__ = _base.Executor.shutdown.__doc__
里面最关键的一个函数是submit，对于线程池调度器来说，不管有多少任务直接往里面提交即可，它会将task放入阻塞队列中，而调度器自己会有一个线程池专门取阻塞队列中的task并执行。另一个值得注意的地方在于submit返回的是future对象，显然，如果想获取task执行之后的结果，也应该从future对象入手。
2.2 Event scheduler
"""A generally useful event scheduler class.
Each instance of this class manages its own queue.
No multi-threading is implied; you are supposed to hack that
yourself, or use a single instance per application.
Each instance is parametrized with two functions, one that is
supposed to return the current time, one that is supposed to
implement a delay. You can implement real-time scheduling by
substituting time and sleep from built-in module time, or you can
implement simulated time by writing your own functions. This can
also be used to integrate scheduling with STDWIN events; the delay
function is allowed to modify the queue. Time can be expressed as
integers or floating point numbers, as long as it is consistent.
Events are specified by tuples (time, priority, action, argument, kwargs).
As in UNIX, lower priority numbers mean higher priority; in this
way the queue can be maintained as a priority queue. Execution of the
event means calling the action function, passing it the argument
sequence in "argument" (remember that in Python, multiple function
arguments are be packed in a sequence) and keyword parameters in "kwargs".
The action function may be an instance method so it
has another way to reference private data (besides global variables).
"""
import time
import heapq
from collections import namedtuple
import threading
from time import monotonic as _time
__all__ = ["scheduler"]
class Event(namedtuple('Event', 'time, priority, action, argument, kwargs')):
__slots__ = []
def __eq__(s, o): return (s.time, s.priority) == (o.time, o.priority)
def __lt__(s, o): return (s.time, s.priority) < (o.time, o.priority)
def __le__(s, o): return (s.time, s.priority) <= (o.time, o.priority)
def __gt__(s, o): return (s.time, s.priority) > (o.time, o.priority)
def __ge__(s, o): return (s.time, s.priority) >= (o.time, o.priority)
Event.time.__doc__ = ('''Numeric type compatible with the return value of the
timefunc function passed to the constructor.''')
Event.priority.__doc__ = ('''Events scheduled for the same time will be executed
in the order of their priority.''')
Event.action.__doc__ = ('''Executing the event means executing
action(*argument, **kwargs)''')
Event.argument.__doc__ = ('''argument is a sequence holding the positional
arguments for the action.''')
Event.kwargs.__doc__ = ('''kwargs is a dictionary holding the keyword
arguments for the action.''')
_sentinel = object()
class scheduler:
def __init__(self, timefunc=_time, delayfunc=time.sleep):
"""Initialize a new instance, passing the time and delay
functions"""
self._queue = []
self._lock = threading.RLock()
self.timefunc = timefunc
self.delayfunc = delayfunc
def enterabs(self, time, priority, action, argument=(), kwargs=_sentinel):
"""Enter a new event in the queue at an absolute time.
Returns an ID for the event which can be used to remove it,
if necessary.
"""
if kwargs is _sentinel:
kwargs = {}
event = Event(time, priority, action, argument, kwargs)
with self._lock:
heapq.heappush(self._queue, event)
return event # The ID
def enter(self, delay, priority, action, argument=(), kwargs=_sentinel):
"""A variant that specifies the time as a relative time.
This is actually the more commonly used interface.
"""
time = self.timefunc() + delay
return self.enterabs(time, priority, action, argument, kwargs)
def cancel(self, event):
"""Remove an event from the queue.
This must be presented the ID as returned by enter().
If the event is not in the queue, this raises ValueError.
"""
with self._lock:
self._queue.remove(event)
heapq.heapify(self._queue)
def empty(self):
"""Check whether the queue is empty."""
with self._lock:
return not self._queue
def run(self, blocking=True):
"""Execute events until the queue is empty.
If blocking is False executes the scheduled events due to
expire soonest (if any) and then return the deadline of the
next scheduled call in the scheduler.
When there is a positive delay until the first event, the
delay function is called and the event is left in the queue;
otherwise, the event is removed from the queue and executed
(its action function is called, passing it the argument). If
the delay function returns prematurely, it is simply
restarted.
It is legal for both the delay function and the action
function to modify the queue or to raise an exception;
exceptions are not caught but the scheduler's state remains
well-defined so run() may be called again.
A questionable hack is added to allow other threads to run:
just after an event is executed, a delay of 0 is executed, to
avoid monopolizing the CPU when other threads are also
runnable.
"""
# localize variable access to minimize overhead
# and to improve thread safety
lock = self._lock
q = self._queue
delayfunc = self.delayfunc
timefunc = self.timefunc
pop = heapq.heappop
while True:
with lock:
if not q:
break
time, priority, action, argument, kwargs = q[0]
now = timefunc()
if time > now:
delay = True
else:
delay = False
pop(q)
if delay:
if not blocking:
return time - now
delayfunc(time - now)
else:
action(*argument, **kwargs)
delayfunc(0) # Let other threads run
@property
def queue(self):
"""An ordered list of upcoming events.
Events are named tuples with fields for:
time, priority, action, arguments, kwargs
"""
# Use heapq to sort the queue rather than using 'sorted(self._queue)'.
# With heapq, two events scheduled at the same time will show in
# the actual order they would be retrieved.
with self._lock:
events = self._queue[:]
return list(map(heapq.heappop, [events]*len(events)))