python多線程

J4ck_Chan 發(fā)布于2019-07-30 18:44 / 3279人閱讀

摘要：對于操作為主的編程來說，多進(jìn)程和多先產(chǎn)出的性能差別不大，甚至多線程比多進(jìn)程的性能還高，因?yàn)槎嗑€程編程更加輕量級。

GIL

global interpreter lock（cpython）

同一時(shí)刻只有一個(gè)線程運(yùn)行在一個(gè)cpu上執(zhí)行字節(jié)碼（無法將多個(gè)線程映射到多個(gè)cpu上）

import dis

def add(a):
    a = a + 1
    return a

print(dis.dis(add))

GIL在某些情況下會釋放

每次的結(jié)果都不一樣線程之間的安全問題

GIL會根據(jù)執(zhí)行的直接碼行數(shù)或者時(shí)間片釋放GIL

遇到IO操作時(shí)主動釋放

total = 0

def add():
    #1. dosomething1
    #2. io操作
    # 1. dosomething3
    global total
    for i in range(1000000):
        total += 1
def desc():
    global total
    for i in range(1000000):
        total -= 1

import threading
thread1 = threading.Thread(target=add)
thread2 = threading.Thread(target=desc)
thread1.start()
thread2.start()

thread1.join()
thread2.join()
print(total)

多線程編程

操作系統(tǒng)能夠調(diào)度的的最小單位是進(jìn)程，因?yàn)檫M(jìn)程對系統(tǒng)的資源消耗非常大，所以后期就演變成了線程，線程實(shí)際上是依賴于我們的進(jìn)程（任務(wù)管理器中我們實(shí)際上能看到的其實(shí)是進(jìn)程），操作系統(tǒng)能調(diào)度的最小單元是線程。

對于io操作為主的編程來說，多進(jìn)程和多先產(chǎn)出的性能差別不大，甚至多線程比多進(jìn)程的性能還高，因?yàn)槎嗑€程編程更加輕量級。

簡單的線程

import time
from threading import Thread


def get_detail_html(url):
    print("get detail html started")
    time.sleep(2)
    print("get detail html end")


def get_detail_url(url):
    print("get detail url started")
    time.sleep(4)
    print("get detail url end")


if __name__ == "__main__":
    thread1 = Thread(target=get_detail_html, args=("",))
    thread2 = Thread(target=get_detail_url, args=("",))
    # 設(shè)置為守護(hù)線程 當(dāng)主線程運(yùn)行完時(shí) 子線程被kill掉
    thread1.setDaemon(True)
    thread2.setDaemon(True)
    start_time = time.time()
    thread1.start()
    thread2.start()

    # 設(shè)置為阻塞 等待線程運(yùn)行完再關(guān)閉主線程
    thread1.join()
    thread2.join()
    # 默認(rèn)情況下 主線程退出與時(shí) 子線程不會被kill掉
    print("last time: {}".format(time.time() - start_time))

重載線程實(shí)現(xiàn)多線程

import time
import threading

def get_detail_html(url):
    print("get detail html started")
    time.sleep(2)
    print("get detail html end")


def get_detail_url(url):
    print("get detail url started")
    time.sleep(4)
    print("get detail url end")


#2. 通過集成Thread來實(shí)現(xiàn)多線程
class GetDetailHtml(threading.Thread):
    def __init__(self, name):
        super().__init__(name=name)

    def run(self):
        print("get detail html started")
        time.sleep(2)
        print("get detail html end")


class GetDetailUrl(threading.Thread):
    def __init__(self, name):
        super().__init__(name=name)

    def run(self):
        print("get detail url started")
        time.sleep(4)
        print("get detail url end")

if  __name__ == "__main__":
    thread1 = GetDetailHtml("get_detail_html")
    thread2 = GetDetailUrl("get_detail_url")
    start_time = time.time()
    thread1.start()
    thread2.start()

    thread1.join()
    thread2.join()

    #當(dāng)主線程退出的時(shí)候， 子線程kill掉
    print ("last time: {}".format(time.time()-start_time))

多線程之間的通信

使用queue

# filename: thread_queue_test.py
# 通過queue的方式進(jìn)行線程間同步
from queue import Queue
import time
import threading


def get_detail_html(queue):
    # 死循環(huán) 爬取文章詳情頁
    while True:
        url = queue.get()
        # for url in detail_url_list:
        print("get detail html started")
        time.sleep(2)
        print("get detail html end")


def get_detail_url(queue):
    # 死循環(huán) 爬取文章列表頁
    while True:
        print("get detail url started")
        time.sleep(4)
        for i in range(20):
            # put 等到有空閑位置 再放入
            # put_nowait 非阻塞方式
            queue.put("http://projectsedu.com/{id}".format(id=i))
        print("get detail url end")


# 1. 線程通信方式- 共享變量
if __name__ == "__main__":
    detail_url_queue = Queue(maxsize=1000)

    thread_detail_url = threading.Thread(target=get_detail_url, args=(detail_url_queue,))
    for i in range(10):
        html_thread = threading.Thread(target=get_detail_html, args=(detail_url_queue,))
        html_thread.start()

    start_time = time.time()
    # 調(diào)用task_down從主線程退出
    detail_url_queue.task_done()
    # 從queue的角度阻塞
    detail_url_queue.join()

    print("last time: {}".format(time.time() - start_time))

線程的同步問題

在多線程編程中必須要面對的問題

無鎖不安全的原因

# 沒有鎖
def add1(a):
    a += 1

def desc1(a):
    a -= 1

"""add
1. load a  a = 0
2. load 1  1
3. +    1
4. 賦值給a a=1
"""

"""add
1. load a  a = 0
2. load 1  1
3. -    1
4. 賦值給a a=-1
"""
import dis
print(dis.dis(add1))
print(dis.dis(desc1))

普通鎖(Lock)

用鎖會影響性能，鎖會引起死鎖（兩次獲取鎖，獲取鎖之后不釋放，互相等待（a需要b的資源 b需要a的資源））

import threading
from threading import Lock

total = 0
# 定義一把鎖
lock = Lock()
def add():
    global total
    global lock
    for i in range(1000000):
        # 獲取鎖
        lock.acquire()
        total += 1
        # 釋放鎖
        lock.release()

def desc():
    global total
    for i in range(1000000):
        lock.acquire()
        total -= 1
        lock.release()

thread1 = threading.Thread(target=add)
thread2 = threading.Thread(target=desc)
thread1.start()
thread2.start()

thread1.join()
thread2.join()
print(total)

相互等待（資源競爭）

"""
A(a、b)
acquire (a)
acquire (b)

B(a、b)
acquire (b)
acquire (a)

# 解決辦法
B(a、b)
acquire (a)
acquire (b)
"""

可重入鎖（Rlock）

import threading
from threading import RLock

total = 0
# 可重入鎖 可以在同一個(gè)線程中可載入多次
lock = RLock()
def add(lock):
    global total
    for i in range(1000000):
        # 獲取鎖
        lock.acquire()
        lock.acquire()
        total += 1
        do_something(lock)
        # 釋放鎖
        lock.release()
        lock.release()

def desc():
    global total
    for i in range(1000000):
        lock.acquire()
        total -= 1
        lock.release()

def do_something(lock):
    lock.acquire()
    # do something
    lock.release()

thread1 = threading.Thread(target=add)
thread2 = threading.Thread(target=desc)
thread1.start()
thread2.start()

thread1.join()
thread2.join()
print(total)

條件變量鎖（condition）

用于復(fù)雜的線程間同步

# 沒有條件鎖 不能實(shí)現(xiàn)對話
import threading


class XiaoAi(threading.Thread):
   def __init__(self, lock):
       super().__init__(name="小愛")
       self.lock = lock

   def run(self):
       self.lock.acquire()
       print("{} : 在 ".format(self.name))
       self.lock.release()

       self.lock.acquire()
       print("{} : 好啊 ".format(self.name))
       self.lock.release()


class TianMao(threading.Thread):
   def __init__(self, lock):
       super().__init__(name="天貓精靈")
       self.lock = lock

   def run(self):
       self.lock.acquire()
       print("{} : 小愛同學(xué) ".format(self.name))
       self.lock.release()

       self.lock.acquire()
       print("{} : 我們來對古詩吧 ".format(self.name))
       self.lock.release()


if __name__ == "__main__":
   cond = threading.Condition()
   xiaoai = XiaoAi(cond)
   tianmao = TianMao(cond)

   xiaoai.start()
   tianmao.start()

# 條件鎖
import threading


class XiaoAi(threading.Thread):
    def __init__(self, cond):
        super().__init__(name="小愛")
        self.cond = cond

    def run(self):
        with self.cond:
            self.cond.wait()
            print("{} : 在 ".format(self.name))
            self.cond.notify()

            self.cond.wait()
            print("{} : 好啊 ".format(self.name))
            self.cond.notify()

            self.cond.wait()
            print("{} : 君住長江尾 ".format(self.name))
            self.cond.notify()

            self.cond.wait()
            print("{} : 共飲長江水 ".format(self.name))
            self.cond.notify()

            self.cond.wait()
            print("{} : 此恨何時(shí)已 ".format(self.name))
            self.cond.notify()

            self.cond.wait()
            print("{} : 定不負(fù)相思意 ".format(self.name))
            self.cond.notify()

class TianMao(threading.Thread):
    def __init__(self, cond):
        super().__init__(name="天貓精靈")
        self.cond = cond

    def run(self):
        with self.cond:
            print("{} : 小愛同學(xué) ".format(self.name))
            self.cond.notify()
            self.cond.wait()

            print("{} : 我們來對古詩吧 ".format(self.name))
            self.cond.notify()
            self.cond.wait()

            print("{} : 我住長江頭 ".format(self.name))
            self.cond.notify()
            self.cond.wait()

            print("{} : 日日思君不見君 ".format(self.name))
            self.cond.notify()
            self.cond.wait()

            print("{} : 此水幾時(shí)休 ".format(self.name))
            self.cond.notify()
            self.cond.wait()

            print("{} : 只愿君心似我心 ".format(self.name))
            self.cond.notify()
            self.cond.wait()



if __name__ == "__main__":
    from concurrent import futures
    cond = threading.Condition()
    xiaoai = XiaoAi(cond)
    tianmao = TianMao(cond)

    # 啟動順序很重要
    # 在調(diào)用with cond之后才能調(diào)用wait或者notify方法
    # condition有兩層鎖， 一把底層鎖會在線程調(diào)用了wait方法的時(shí)候釋放，
    # 上面的鎖會在每次調(diào)用wait的時(shí)候分配一把并放入到cond的等待隊(duì)列中，
    # 等到notify方法的喚醒
    xiaoai.start()
    tianmao.start()