Python 小手册 - 线程与进程

Python 小手册 - 线程与进程
- 进程与线程
- 进程
  - Process
  - Lock
  - Semaphore
  - Event
  - Queue
  - Pipe
  - Pool
- 线程
  - 创建线程
  - lock

Python 小手册 - 线程与进程

提示：本文档以python2.7版本为例

进程与线程

进程不共享内存，线程是共享内存的
进程至少有一个线程
进程中所包含的一个或多个执行单元称为线程,线程是处理器调度的基本单位.
线程不能单独运行
多线程在cpu上，同时只能运行一个
多线程不能跨cpu运行
多线程的运行顺序可以是不确定的、随机的、不可预测的。
线程只有 3 个基本状态：就绪，执行，阻塞。
线程存在 5 种基本操作来切换线程的状态：派生，阻塞，激活，调度，结束。
单机系统中进程通信有 4 种形式：主从式，会话式，消息或邮箱机制，共享存储区方式。主从式典型例子：终端控制进程和终端进程。会话式典型例子：用户进程与磁盘管理进程之间的通信。

进程

Process

创建进程的类：

Process([group [, target [, name [, args [, kwargs]]]]])

target表示调用对象，args表示调用对象的位置参数元组。kwargs表示调用对象的字典。name为别名。group实质上不使用。

方法：is_alive()、join([timeout])、run()、start()、terminate()。其中，Process以start()启动某个进程。

属性：authkey、daemon（要通过start()设置）、exitcode(进程在运行时为None、如果为–N，表示被信号N结束）、name、pid。其中daemon是父进程终止后自动终止，且自己不能产生新进程，必须在start()之前设置。

例：创建函数并将其作为单个进程

import multiprocessing
import time

def worker(interval):
	n = 5
	while n > 0:
		print "The time is {0}".format(time.ctime())
		time.sleep(interval)
		n -= 1

if __name__ == "__main__":
	p = multiprocessing.Process(target = worker, args = (3,))
	p.start()
	print "p.pid:", p.pid
	print "p.name:", p.name
	print "p.is_alive:", p.is_alive()

----
p.pid: 11124
p.name: Process-1
p.is_alive: True
The time is Fri Jul 29 16:10:03 2016
The time is Fri Jul 29 16:10:06 2016
The time is Fri Jul 29 16:10:09 2016
The time is Fri Jul 29 16:10:12 2016
The time is Fri Jul 29 16:10:15 2016

例：创建函数并将其作为多个进程

import multiprocessing
import time

def worker_1(interval):
    print "worker_1"
    time.sleep(interval)
    print "end worker_1"

def worker_2(interval):
    print "worker_2"
    time.sleep(interval)
    print "end worker_2"

def worker_3(interval):
    print "worker_3"
    time.sleep(interval)
    print "end worker_3"

if __name__ == "__main__":
    p1 = multiprocessing.Process(target = worker_1, args = (2,))
    p2 = multiprocessing.Process(target = worker_2, args = (3,))
    p3 = multiprocessing.Process(target = worker_3, args = (4,))

    p1.start()
    p2.start()
    p3.start()

    print "The number of CPU is:" + str(multiprocessing.cpu_count())
    for p in multiprocessing.active_children():
        print "child   p.name:" + p.name + "\tp.id" + str(p.pid)
    print "END"

----
The number of CPU is:8
child   p.name:Process-2	p.id8824
child   p.name:Process-1	p.id11048
child   p.name:Process-3	p.id2116
END
worker_1
worker_2
worker_3
end worker_1
end worker_2
end worker_3

例：将进程定义为类

import multiprocessing
import time


class ClockProcess(multiprocessing.Process):
    def __init__(self, interval):
        multiprocessing.Process.__init__(self)
        self.interval = interval

    def run(self):
        n = 5
        while n > 0:
            print "the time is {0}".format(time.ctime())
            time.sleep(self.interval)
            n -= 1

if __name__ == '__main__':
    p = ClockProcess(3)
    p.start()


----
the time is Fri Jul 29 16:14:51 2016
the time is Fri Jul 29 16:14:54 2016
the time is Fri Jul 29 16:14:57 2016
the time is Fri Jul 29 16:15:00 2016
the time is Fri Jul 29 16:15:03 2016

注：进程p调用start()时，自动调用run()

例1.4：daemon程序对比结果

不加daemon属性

import multiprocessing
import time


def worker(interval):
    print "work start:{0}".format(time.ctime())
    time.sleep(interval)
    print "work end:{0}".format(time.ctime())

if __name__ == "__main__":
    p = multiprocessing.Process(target=worker, args=(3,))
    p.start()
    print "end!"

----
end!
work start:Fri Jul 29 16:17:12 2016
work end:Fri Jul 29 16:17:15 2016

上daemon属性

import multiprocessing
import time

def worker(interval):
    print "work start:{0}".format(time.ctime())
    time.sleep(interval)
    print "work end:{0}".format(time.ctime())

if __name__ == "__main__":
    p = multiprocessing.Process(target=worker, args=(3,))
    p.daemon = True
    p.start()
    print "end!"

----
end!

注：因子进程设置了daemon属性，主进程结束，它们就随着结束了。

设置daemon执行完结束的方法

import multiprocessing
import time


def worker(interval):
    print("work start:{0}".format(time.ctime()))
    time.sleep(interval)
    print("work end:{0}".format(time.ctime()))

if __name__ == "__main__":
    p = multiprocessing.Process(target=worker, args=(3,))
    p.daemon = True
    p.start()
    p.join()
    print "end!"

----
work start:Fri Jul 29 16:20:19 2016
work end:Fri Jul 29 16:20:22 2016
end!

join()方法是等待子进程结束后再继续往下运行，通常用于进程间的同步。

Lock

当多个进程需要访问共享资源的时候，Lock可以用来避免访问的冲突。

import multiprocessing
import sys


def worker_with(lock, f):
    with lock:
        fs = open(f, 'a+')
        n = 10
        while n > 1:
            fs.write("Lockd acquired via with\n")
            n -= 1
        fs.close()
        
def worker_no_with(lock, f):
    lock.acquire()
    try:
        fs = open(f, 'a+')
        n = 10
        while n > 1:
            fs.write("Lock acquired directly\n")
            n -= 1
        fs.close()
    finally:
        lock.release()
    
if __name__ == "__main__":
    lock = multiprocessing.Lock()
    f = "file.txt"
    w = multiprocessing.Process(target = worker_with, args=(lock, f))
    nw = multiprocessing.Process(target = worker_no_with, args=(lock, f))
    w.start()
    nw.start()
    print "end"


# 结果（输出文件）

Lockd acquired via with
Lockd acquired via with
Lockd acquired via with
Lockd acquired via with
Lockd acquired via with
Lockd acquired via with
Lockd acquired via with
Lockd acquired via with
Lockd acquired via with
Lock acquired directly
Lock acquired directly
Lock acquired directly
Lock acquired directly
Lock acquired directly
Lock acquired directly
Lock acquired directly
Lock acquired directly
Lock acquired directly

lock.acquire() 获取锁 lock.release() 释放锁

Semaphore

Semaphore用来控制对共享资源的访问数量，例如池的最大连接数。

import multiprocessing
import time


def worker(s, i):
    s.acquire()
    print multiprocessing.current_process().name + "acquire"
    time.sleep(i)
    print multiprocessing.current_process().name + "release\n"
    s.release()

if __name__ == "__main__":
    s = multiprocessing.Semaphore(2)
    for i in range(5):
        p = multiprocessing.Process(target = worker, args=(s, i*2))
        p.start()


---

Process-1acquire
Process-1release

Process-2acquire
Process-4acquire
Process-2release

Process-3acquire
Process-3release

Process-5acquire
Process-4release

Process-5release

Event

Event用来实现进程间同步通信。

import multiprocessing
import time


def wait_for_event(e):
    print "wait_for_event: starting"
    e.wait()
    print "wairt_for_event: e.is_set()->" + str(e.is_set())


def wait_for_event_timeout(e, t):
    print "wait_for_event_timeout:starting"
    e.wait(t)
    print "wait_for_event_timeout:e.is_set->" + str(e.is_set())


if __name__ == "__main__":
    e = multiprocessing.Event()
    w1 = multiprocessing.Process(name="block",
                                 target=wait_for_event,
                                 args=(e,))

    w2 = multiprocessing.Process(name="non-block",
                                 target=wait_for_event_timeout,
                                 args=(e, 2))
    w1.start()
    w2.start()

    time.sleep(3)

    e.set()
    print "main: event is set"

---
wait_for_event_timeout:starting
wait_for_event: starting
wait_for_event_timeout:e.is_set->False
main: event is set
wairt_for_event: e.is_set()->True

Queue

Queue是多进程安全的队列，可以使用Queue实现多进程之间的数据传递。put方法用以插入数据到队列中，put方法还有两个可选参数：blocked和timeout。如果blocked为True（默认值），并且timeout为正值，该方法会阻塞timeout指定的时间，直到该队列有剩余的空间。如果超时，会抛出Queue.Full异常。如果blocked为False，但该Queue已满，会立即抛出Queue.Full异常。

get方法可以从队列读取并且删除一个元素。同样，get方法有两个可选参数：blocked和timeout。如果blocked为True（默认值），并且timeout为正值，那么在等待时间内没有取到任何元素，会抛出Queue.Empty异常。如果blocked为False，有两种情况存在，如果Queue有一个值可用，则立即返回该值，否则，如果队列为空，则立即抛出Queue.Empty异常。

Queue的一段示例代码：

import multiprocessing


def writer_proc(q):      
    try:         
        q.put(1, block = False) 
    except:         
        pass   

def reader_proc(q):      
    try:         
        print q.get(block = False) 
    except:         
        pass

if __name__ == "__main__":
    q = multiprocessing.Queue()
    writer = multiprocessing.Process(target=writer_proc, args=(q,))  
    writer.start()   

    reader = multiprocessing.Process(target=reader_proc, args=(q,))  
    reader.start()  

    reader.join()  
    writer.join()

----
1

Pipe

Pipe方法返回(conn1, conn2)代表一个管道的两个端。Pipe方法有duplex参数，如果duplex参数为True(默认值)，那么这个管道是全双工模式，也就是说conn1和conn2均可收发。duplex为False，conn1只负责接受消息，conn2只负责发送消息。

send和recv方法分别是发送和接受消息的方法。例如，在全双工模式下，可以调用conn1.send发送消息，conn1.recv接收消息。如果没有消息可接收，recv方法会一直阻塞。如果管道已经被关闭，那么recv方法会抛出EOFError。

import multiprocessing
import time


def proc1(pipe):
    while True:
        for i in xrange(10000):
            print "send: %s" % (i)
            pipe.send(i)
            time.sleep(1)


def proc2(pipe):
    while True:
        print "proc2 rev:", pipe.recv()
        time.sleep(1)


def proc3(pipe):
    while True:
        print "PROC3 rev:", pipe.recv()
        time.sleep(1)


if __name__ == "__main__":
    pipe = multiprocessing.Pipe()
    p1 = multiprocessing.Process(target=proc1, args=(pipe[0],))
    p2 = multiprocessing.Process(target=proc2, args=(pipe[1],))
    # p3 = multiprocessing.Process(target=proc3, args=(pipe[1],))

    p1.start()
    p2.start()
    # p3.start()

    p1.join()
    p2.join()
    # p3.join()

----
send: 0
proc2 rev: 0
send: 1
proc2 rev: 1
send: 2
proc2 rev: 2
send: 3
proc2 rev: 3
...

Pool

在利用Python进行系统管理的时候，特别是同时操作多个文件目录，或者远程控制多台主机，并行操作可以节约大量的时间。当被操作对象数目不大时，可以直接利用multiprocessing中的Process动态成生多个进程，十几个还好，但如果是上百个，上千个目标，手动的去限制进程数量却又太过繁琐，此时可以发挥进程池的功效。 Pool可以提供指定数量的进程，供用户调用，当有新的请求提交到pool中时，如果池还没有满，那么就会创建一个新的进程用来执行该请求；但如果池中的进程数已经达到规定最大值，那么该请求就会等待，直到池中有进程结束，才会创建新的进程来它。

例：使用进程池（非阻塞）

# coding: utf-8
import multiprocessing
import time


def func(msg):
    print "msg:", msg
    time.sleep(3)
    print "end"


if __name__ == "__main__":
    pool = multiprocessing.Pool(processes=3)
    for i in xrange(4):
        msg = "hello %d" % i
        pool.apply_async(func, (msg,))  # 维持执行的进程总数为processes，当一个进程执行完毕后会添加新的进程进去

    print "~~~~~~~~~~~~~~~~~~~~~~"
    pool.close()
    pool.join()  # 调用join之前，先调用close函数，否则会出错。执行完close后不会有新的进程加入到pool,join函数等待所有子进程结束
    print "Sub-process(es) done."

----
~~~~~~~~~~~~~~~~~~~~~~
msg: hello 0
msg: hello 1
msg: hello 2
end
end
msg: hello 3
end
end
Sub-process(es) done.

函数解释：

apply_async(func[, args[, kwds[, callback]]]) 它是非阻塞，apply(func[, args[, kwds]])是阻塞的（理解区别，看例1例2结果区别）
close() 关闭pool，使其不在接受新的任务。
terminate() 结束工作进程，不在处理未完成的任务。
join() 主进程阻塞，等待子进程的退出， join方法要在close或terminate之后使用。

执行说明：创建一个进程池pool，并设定进程的数量为3，xrange(4)会相继产生四个对象[0, 1, 2, 4]，四个对象被提交到pool中，因pool指定进程数为3，所以0、1、2会直接送到进程中执行，当其中一个执行完事后才空出一个进程处理对象3，所以会出现输出“msg: hello 3”出现在”end”后。因为为非阻塞，主函数会自己执行自个的，不搭理进程的执行，所以运行完for循环后直接输出“~~~~~~~~~~~~~~~~~~~~~~”，主程序在pool.join（）处等待各个进程的结束。

例：使用进程池（阻塞）

# coding: utf-8
import multiprocessing
import time


def func(msg):
    print "msg:", msg
    time.sleep(3)
    print "end"


if __name__ == "__main__":
    pool = multiprocessing.Pool(processes=3)
    for i in xrange(4):
        msg = "hello %d" % i
        pool.apply(func, (msg,))  # 维持执行的进程总数为processes，当一个进程执行完毕后会添加新的进程进去

    print "~~~~~~~~~~~~~~~~~~~~~~"
    pool.close()
    pool.join()  # 调用join之前，先调用close函数，否则会出错。执行完close后不会有新的进程加入到pool,join函数等待所有子进程结束
    print "Sub-process(es) done."

----
msg: hello 0
end
msg: hello 1
end
msg: hello 2
end
msg: hello 3
end
~~~~~~~~~~~~~~~~~~~~~~
Sub-process(es) done.

例：使用进程池，并关注结果

import multiprocessing
import time


def func(msg):
    print "msg:", msg
    time.sleep(3)
    print "end"
    return "done:" + msg


if __name__ == "__main__":
    pool = multiprocessing.Pool(processes=4)
    result = []
    for i in xrange(3):
        msg = "hello %d" % i
        result.append(pool.apply_async(func, (msg,)))
    pool.close()
    pool.join()
    for res in result:
        print ":::", res.get()
    print "Sub-process(es) done."

----
msg: hello 0
msg: hello 1
msg: hello 2
end
end
end
::: done:hello 0
::: done:hello 1
::: done:hello 2
Sub-process(es) done.

例：使用多个进程池

# coding: utf-8
import multiprocessing
import os
import random
import time


def Lee():
    print "\nRun task Lee-%s" % (os.getpid())  # os.getpid()获取当前的进程的ID
    start = time.time()
    time.sleep(random.random() * 10)  # random.random()随机生成0-1之间的小数
    end = time.time()
    print 'Task Lee, runs %0.2f seconds.' % (end - start)


def Marlon():
    print "\nRun task Marlon-%s" % (os.getpid())
    start = time.time()
    time.sleep(random.random() * 40)
    end = time.time()
    print 'Task Marlon runs %0.2f seconds.' % (end - start)


def Allen():
    print "\nRun task Allen-%s" % (os.getpid())
    start = time.time()
    time.sleep(random.random() * 30)
    end = time.time()
    print 'Task Allen runs %0.2f seconds.' % (end - start)


def Frank():
    print "\nRun task Frank-%s" % (os.getpid())
    start = time.time()
    time.sleep(random.random() * 20)
    end = time.time()
    print 'Task Frank runs %0.2f seconds.' % (end - start)


if __name__ == '__main__':
    function_list = [Lee, Marlon, Allen, Frank]
    print "parent process %s" % (os.getpid())

    pool = multiprocessing.Pool(4)
    for func in function_list:
        pool.apply_async(func)  # Pool执行函数，apply执行函数,当有一个进程执行完毕后，会添加一个新的进程到pool中

    print 'Waiting for all subprocesses done...'
    pool.close()
    pool.join()  # 调用join之前，一定要先调用close() 函数，否则会出错, close()执行后不会有新的进程加入到pool,join函数等待素有子进程结束
    print 'All subprocesses done.'


----
parent process 9960
Waiting for all subprocesses done...

Run task Lee-9020

Run task Marlon-5596

Run task Allen-10560

Run task Frank-11168
Task Lee, runs 0.69 seconds.
Task Frank runs 5.44 seconds.
Task Allen runs 22.02 seconds.
Task Marlon runs 37.72 seconds.
All subprocesses done.

例：使用pool map

import multiprocessing

def m1(x):
    return x * x

if __name__ == '__main__':
    pool = multiprocessing.Pool(processes=3)
    print pool.map(m1, [1, 2, 3, 4])

----
[1, 4, 9, 16]

import multiprocessing


def create_logger(i):
    print i


class CreateLogger(object):
    def __init__(self, func):
        self.func = func


if __name__ == '__main__':
    ilist = range(10)

    cl = CreateLogger(create_logger)
    pool = multiprocessing.Pool(multiprocessing.cpu_count())
    pool.map(cl.func, ilist)

    print "hello------------>"

----
0
1
2
3
4
5
6
7
8
9
hello------------>

线程

创建线程

import thread
import time


# 为线程定义一个函数
def print_time(name, delay):
    count = 0
    while count < 2:
        time.sleep(delay)
        count += 1
        print "%s: %s" % (name, time.ctime(time.time()))
    thread.exit_thread()

# 创建两个线程
try:
    thread.start_new_thread(print_time, ("Thread-1", 2,))
    thread.start_new_thread(print_time, ("Thread-2", 4,))
except:
    print "Error: unable to start thread"

time.sleep(10)

print 'stop.'

----
Thread-1: Wed Aug 03 09:58:26 2016
Thread-1: Wed Aug 03 09:58:28 2016Thread-2: Wed Aug 03 09:58:28 2016

Thread-2: Wed Aug 03 09:58:32 2016
stop.

import time, threading


def loop():
    print 'thread %s is running...' % threading.current_thread().name
    n = 0
    while n < 5:
        n += 1
        print 'thread %s >>> %s' % (threading.current_thread().name, n)
        time.sleep(1)
    print 'thread %s ended.' % threading.current_thread().name


print 'thread %s is running...' % threading.current_thread().name
t = threading.Thread(target=loop, name='LoopThread')
t.start()
t.join()
print 'thread %s ended.' % threading.current_thread().name

----

thread MainThread is running...
thread LoopThread is running...
thread LoopThread >>> 1
thread LoopThread >>> 2
thread LoopThread >>> 3
thread LoopThread >>> 4
thread LoopThread >>> 5
thread LoopThread ended.
thread MainThread ended.

lock

# coding=utf-8
import threading

# 假定这是你的银行存款:
balance = 0
lock = threading.Lock()


def change_it(n):
    # 先存后取，结果应该为0:
    global balance
    balance = balance + n
    balance = balance - n


def run_thread(n):
    for i in range(100000):
        # 先要获取锁:
        lock.acquire()
        try:
            # 放心地改吧:
            change_it(n)
        finally:
            # 改完了一定要释放锁:
            lock.release()

t1 = threading.Thread(target=run_thread, args=(5,))
t2 = threading.Thread(target=run_thread, args=(8,))
t1.start()
t2.start()
t1.join()
t2.join()

print balance

----
0

Python 小手册 - 线程与进程