Python子进程并行

假设您有一个随机打印行的脚本：

#!/usr/bin/env python
#file: child.py
import os
import random
import sys
import time

for i in range(10):
    print("%2d %s %s" % (int(sys.argv[1]),os.getpid(),i))
    sys.stdout.flush()
    time.sleep(random.random())

并且您希望在输出可用后立即收集输出,您可以在POSIX系统上使用select作为@zigg suggested：

#!/usr/bin/env python
from __future__ import print_function
from select     import select
from subprocess import Popen,PIPE

# start several subprocesses
processes = [Popen(['./child.py',str(i)],stdout=PIPE,bufsize=1,close_fds=True,universal_newlines=True)
             for i in range(5)]

# read output
timeout = 0.1 # seconds
while processes:
    # remove finished processes from the list (O(N**2))
    for p in processes[:]:
        if p.poll() is not None: # process ended
            print(p.stdout.read(),end='') # read the rest
            p.stdout.close()
            processes.remove(p)

    # wait until there is something to read
    rlist = select([p.stdout for p in processes],[],timeout)[0]

    # read a line from each process that has output ready
    for f in rlist:
        print(f.readline(),end='') #NOTE: it can block

更便携的解决方案(适用于Windows,Linux,OSX)可以为每个进程使用读取器线程,请参阅Non-blocking read on a subprocess.PIPE in python.

这是基于os.pipe()的解决方案,适用于Unix和Windows：

#!/usr/bin/env python
from __future__ import print_function
import io
import os
import sys
from subprocess import Popen

ON_POSIX = 'posix' in sys.builtin_module_names

# create a pipe to get data
input_fd,output_fd = os.pipe()

# start several subprocesses
processes = [Popen([sys.executable,'child.py',stdout=output_fd,close_fds=ON_POSIX) # close input_fd in children
             for i in range(5)]
os.close(output_fd) # close unused end of the pipe

# read output line by line as soon as it is available
with io.open(input_fd,'r',buffering=1) as file:
    for line in file:
        print(line,end='')
#
for p in processes:
    p.wait()