我可以假设我的线程在 threading.active_count() returns 1 时完成吗？

Question

给出以下 class：

from abc import ABCMeta, abstractmethod
from time import sleep
import threading
from threading import active_count, Thread

class ScraperPool(metaclass=ABCMeta):
    Queue = []
    ResultList = []

    def __init__(self, Queue, MaxNumWorkers=0, ItemsPerWorker=50):
        # Initialize attributes
        self.MaxNumWorkers = MaxNumWorkers
        self.ItemsPerWorker = ItemsPerWorker
        self.Queue = Queue # For testing purposes.

    def initWorkerPool(self, PrintIDs=True):
        for w in range(self.NumWorkers()):
            Thread(target=self.worker, args=(w + 1, PrintIDs,)).start()
            sleep(1) # Explicitly wait one second for this worker to start.

    def run(self):
        self.initWorkerPool()

        # Wait until all workers (i.e. threads) are done.
        while active_count() > 1:
            print("Active threads: " + str(active_count()))
            sleep(5)

        self.HandleResults()

    def worker(self, id, printID):
        if printID:
            print("Starting worker " + str(id) + ".")

        while (len(self.Queue) > 0):
            self.scraperMethod()

        if printID:
            print("Worker " + str(id) + " is quiting.")

        # Todo Kill is this Thread.

        return

    def NumWorkers(self):
        return 1 # Simplified for testing purposes.

    @abstractmethod
    def scraperMethod(self): 
        pass

class TestScraper(ScraperPool):
    def scraperMethod(self):
        # print("I am scraping.")
        # print("Scraping. Threads#: " + str(active_count()))
        temp_item = self.Queue[-1]
        self.Queue.pop()

        self.ResultList.append(temp_item)

    def HandleResults(self):
        print(self.ResultList)

ScraperPool.register(TestScraper)

scraper = TestScraper(Queue=["Jaap", "Piet"])
scraper.run()
print(threading.active_count())
# print(scraper.ResultList)

当所有线程都完成后，仍然有一个活动线程 - 最后一行的 threading.active_count() 得到了那个数字。

活动线程是 <_MainThread(MainThread, started 12960)> - 如 threading.enumerate() 所示。

我可以假设我的所有线程都在 active_count() == 1 时完成了吗？或者，例如，导入的模块可以启动额外的线程，以便我的线程在 active_count() > 1 时实际完成 - 这也是我在运行方法中使用的循环条件。

Answer 1

根据 docs active_count() 包括主线程，所以如果你在 1 那么你很可能已经完成了，但是如果你的程序中有另一个新线程源那么你可能会在 active_count() 命中 1 之前完成。

我建议在您的 ScraperPool 上实施明确的 join 方法并跟踪您的工作人员并在需要时明确地将他们加入主线程，而不是检查您是否已完成 [=10] =]来电。

还记得 GIL...

Answer 2

你可以假设你的线程在 active_count() 达到 1 时完成。问题是，如果任何其他模块创建线程，你永远不会达到 1。你应该明确地管理你的线程。

示例：您可以将线程放在一个列表中，然后一次加入一个。您的代码的相关更改是：

def __init__(self, Queue, MaxNumWorkers=0, ItemsPerWorker=50):
    # Initialize attributes
    self.MaxNumWorkers = MaxNumWorkers
    self.ItemsPerWorker = ItemsPerWorker
    self.Queue = Queue # For testing purposes.
    self.WorkerThreads = []

def initWorkerPool(self, PrintIDs=True):
    for w in range(self.NumWorkers()):
        thread = Thread(target=self.worker, args=(w + 1, PrintIDs,))
        self.WorkerThreads.append(thread)
        thread.start()
        sleep(1) # Explicitly wait one second for this worker to start.

def run(self):
    self.initWorkerPool()

    # Wait until all workers (i.e. threads) are done. Waiting in order
    # so some threads further in the list may finish first, but we
    # will get to all of them eventually
    while self.WorkerThreads:
        self.WorkerThreads[0].join()

    self.HandleResults()

我可以假设我的线程在 threading.active_count() returns 1 时完成吗？

Can I assume my threads are done when threading.active_count() returns 1?

python

multithreading

python-multithreading