GIL
在Python中,由于历史原因(GIL),使得Python中多线程的效果非常不理想.GIL使得任何时刻Python只能利用一个CPU核,并且它的调度算法简单粗暴:多线程中,让每个线程运行一段时间t,然后强行挂起该线程,继而去运行其他线程,如此周而复始,直到所有线程结束.
这使得无法有效利用计算机系统中的"局部性",频繁的线程切换也对缓存不是很友好,造成资源的浪费.
据说Python官方曾经实现了一个去除GIL的Python解释器,但是其效果还不如有GIL的解释器,遂放弃.后来Python官方推出了"利用多进程替代多线程"的方案,在Python3中也有concurrent.futures这样的包,让我们的程序编写可以做到"简单和性能兼得".
多进程/多线程+Queue
一般来说,在Python中编写并发程序的经验是:计算密集型任务使用多进程,IO密集型任务使用多进程或者多线程.另外,因为涉及到资源共享,所以需要同步锁等一系列麻烦的步骤,代码编写不直观.另外一种好的思路是利用多进程/多线程+Queue的方法,可以避免加锁这样麻烦低效的方式.
现在在Python2中利用Queue+多进程的方法来处理一个IO密集型任务.
假设现在需要下载多个网页内容并进行解析,单进程的方式效率很低,所以使用多进程/多线程势在必行.
我们可以先初始化一个tasks队列,里面将要存储的是一系列dest_url,同时开启4个进程向tasks中取任务然后执行,处理结果存储在一个results队列中,最后对results中的结果进行解析.最后关闭两个队列.
下面是一些主要的逻辑代码.
# -*- coding:utf-8 -*- #IO密集型任务 #多个进程同时下载多个网页 #利用Queue+多进程 #由于是IO密集型,所以同样可以利用threading模块 import multiprocessing def main(): tasks = multiprocessing.JoinableQueue() results = multiprocessing.Queue() cpu_count = multiprocessing.cpu_count() #进程数目==CPU核数目 create_process(tasks, results, cpu_count) #主进程马上创建一系列进程,但是由于阻塞队列tasks开始为空,副进程全部被阻塞 add_tasks(tasks) #开始往tasks中添加任务 parse(tasks, results) #最后主进程等待其他线程处理完成结果 def create_process(tasks, results, cpu_count): for _ in range(cpu_count): p = multiprocessing.Process(target=_worker, args=(tasks, results)) #根据_worker创建对应的进程 p.daemon = True #让所有进程可以随主进程结束而结束 p.start() #启动 def _worker(tasks, results): while True: #因为前面所有线程都设置了daemon=True,故不会无限循环 try: task = tasks.get() #如果tasks中没有任务,则阻塞 result = _download(task) results.put(result) #some exceptions do not handled finally: tasks.task_done() def add_tasks(tasks): for url in get_urls(): #get_urls() return a urls_list tasks.put(url) def parse(tasks, results): try: tasks.join() except KeyboardInterrupt as err: print "Tasks has been stopped!" print err while not results.empty(): _parse(results) if __name__ == '__main__': main()
利用Python3中的concurrent.futures包
在Python3中可以利用concurrent.futures包,编写更加简单易用的多线程/多进程代码.其使用感觉和Java的concurrent框架很相似(借鉴?)
比如下面的简单代码示例
def handler(): futures = set() with concurrent.futures.ProcessPoolExecutor(max_workers=cpu_count) as executor: for task in get_task(tasks): future = executor.submit(task) futures.add(future) def wait_for(futures): try: for future in concurrent.futures.as_completed(futures): err = futures.exception() if not err: result = future.result() else: raise err except KeyboardInterrupt as e: for future in futures: future.cancel() print "Task has been canceled!" print e return result
总结
要是一些大型Python项目也这般编写,那么效率也太低了.在Python中有许多已有的框架使用,使用它们起来更加高效.
但是自己的一些"小打小闹"的程序这样来编写还是不错的.:)

InPython,youappendelementstoalistusingtheappend()method.1)Useappend()forsingleelements:my_list.append(4).2)Useextend()or =formultipleelements:my_list.extend(another_list)ormy_list =[4,5,6].3)Useinsert()forspecificpositions:my_list.insert(1,5).Beaware

The methods to debug the shebang problem include: 1. Check the shebang line to make sure it is the first line of the script and there are no prefixed spaces; 2. Verify whether the interpreter path is correct; 3. Call the interpreter directly to run the script to isolate the shebang problem; 4. Use strace or trusts to track the system calls; 5. Check the impact of environment variables on shebang.

Pythonlistscanbemanipulatedusingseveralmethodstoremoveelements:1)Theremove()methodremovesthefirstoccurrenceofaspecifiedvalue.2)Thepop()methodremovesandreturnsanelementatagivenindex.3)Thedelstatementcanremoveanitemorslicebyindex.4)Listcomprehensionscr

Pythonlistscanstoreanydatatype,includingintegers,strings,floats,booleans,otherlists,anddictionaries.Thisversatilityallowsformixed-typelists,whichcanbemanagedeffectivelyusingtypechecks,typehints,andspecializedlibrarieslikenumpyforperformance.Documenti

Pythonlistssupportnumerousoperations:1)Addingelementswithappend(),extend(),andinsert().2)Removingitemsusingremove(),pop(),andclear().3)Accessingandmodifyingwithindexingandslicing.4)Searchingandsortingwithindex(),sort(),andreverse().5)Advancedoperatio

Create multi-dimensional arrays with NumPy can be achieved through the following steps: 1) Use the numpy.array() function to create an array, such as np.array([[1,2,3],[4,5,6]]) to create a 2D array; 2) Use np.zeros(), np.ones(), np.random.random() and other functions to create an array filled with specific values; 3) Understand the shape and size properties of the array to ensure that the length of the sub-array is consistent and avoid errors; 4) Use the np.reshape() function to change the shape of the array; 5) Pay attention to memory usage to ensure that the code is clear and efficient.

BroadcastinginNumPyisamethodtoperformoperationsonarraysofdifferentshapesbyautomaticallyaligningthem.Itsimplifiescode,enhancesreadability,andboostsperformance.Here'showitworks:1)Smallerarraysarepaddedwithonestomatchdimensions.2)Compatibledimensionsare

ForPythondatastorage,chooselistsforflexibilitywithmixeddatatypes,array.arrayformemory-efficienthomogeneousnumericaldata,andNumPyarraysforadvancednumericalcomputing.Listsareversatilebutlessefficientforlargenumericaldatasets;array.arrayoffersamiddlegro


Hot AI Tools

Undresser.AI Undress
AI-powered app for creating realistic nude photos

AI Clothes Remover
Online AI tool for removing clothes from photos.

Undress AI Tool
Undress images for free

Clothoff.io
AI clothes remover

Video Face Swap
Swap faces in any video effortlessly with our completely free AI face swap tool!

Hot Article

Hot Tools

WebStorm Mac version
Useful JavaScript development tools

SublimeText3 Mac version
God-level code editing software (SublimeText3)

PhpStorm Mac version
The latest (2018.2.1) professional PHP integrated development tool

Dreamweaver CS6
Visual web development tools

SAP NetWeaver Server Adapter for Eclipse
Integrate Eclipse with SAP NetWeaver application server.
