下面是运行任意命令返回其标准输出数据的Python代码,或在非零退出码上引发异常:

proc = subprocess.Popen(
    cmd,
    stderr=subprocess.STDOUT,  # Merge stdout and stderr
    stdout=subprocess.PIPE,
    shell=True)

communication用于等待进程退出:

stdoutdata, stderrdata = proc.communicate()

子进程模块不支持超时——杀死运行超过X秒的进程的能力——因此,通信可能需要很长时间才能运行。

在Windows和Linux上运行的Python程序中实现超时的最简单方法是什么?


当前回答

不幸的是,我的雇主在公开源代码方面有非常严格的规定,所以我不能提供实际的代码。但对我来说,最好的解决方案是创建一个子类重写Popen.wait()来轮询,而不是无限期地等待。__init__接受超时参数。一旦你这样做,所有其他Popen方法(调用等待)将按预期工作,包括通信。

其他回答

我有一个问题,我想终止一个多线程子进程,如果它花费的时间超过给定的超时长度。我想在Popen()中设置一个超时,但它不起作用。然后,我意识到Popen().wait()等于call(),所以我有了在.wait(timeout=xxx)方法中设置超时的想法,这最终工作了。因此,我是这样解决的:

import os
import sys
import signal
import subprocess
from multiprocessing import Pool

cores_for_parallelization = 4
timeout_time = 15  # seconds

def main():
    jobs = [...YOUR_JOB_LIST...]
    with Pool(cores_for_parallelization) as p:
        p.map(run_parallel_jobs, jobs)

def run_parallel_jobs(args):
    # Define the arguments including the paths
    initial_terminal_command = 'C:\\Python34\\python.exe'  # Python executable
    function_to_start = 'C:\\temp\\xyz.py'  # The multithreading script
    final_list = [initial_terminal_command, function_to_start]
    final_list.extend(args)

    # Start the subprocess and determine the process PID
    subp = subprocess.Popen(final_list)  # starts the process
    pid = subp.pid

    # Wait until the return code returns from the function by considering the timeout. 
    # If not, terminate the process.
    try:
        returncode = subp.wait(timeout=timeout_time)  # should be zero if accomplished
    except subprocess.TimeoutExpired:
        # Distinguish between Linux and Windows and terminate the process if 
        # the timeout has been expired
        if sys.platform == 'linux2':
            os.kill(pid, signal.SIGTERM)
        elif sys.platform == 'win32':
            subp.terminate()

if __name__ == '__main__':
    main()

python 2.7

import time
import subprocess

def run_command(cmd, timeout=0):
    start_time = time.time()
    df = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
    while timeout and df.poll() == None:
        if time.time()-start_time >= timeout:
            df.kill()
            return -1, ""
    output = '\n'.join(df.communicate()).strip()
    return df.returncode, output

不幸的是,我的雇主在公开源代码方面有非常严格的规定,所以我不能提供实际的代码。但对我来说,最好的解决方案是创建一个子类重写Popen.wait()来轮询,而不是无限期地等待。__init__接受超时参数。一旦你这样做,所有其他Popen方法(调用等待)将按预期工作,包括通信。

一旦你理解了在*unix中运行机器的整个过程,你将很容易找到更简单的解决方案:

考虑这个简单的例子,如何使用select.select()(现在几乎在*nix上随处可见)创建可超时的communication()冰毒。这也可以用epoll/poll/kqueue来编写,但select.select()变体可能是一个很好的例子。select.select()的主要限制(速度和1024 max fds)不适用于您的任务。

它在*nix下工作,不创建线程,不使用信号,可以从任何线程启动(不仅仅是主线程),并且足够快,可以从我机器上的stdout读取250mb/s的数据(i5 2.3ghz)。

在通信结束时连接stdout/stderr时出现问题。如果你有大量的程序输出,这可能会导致大量的内存使用。但是您可以多次调用communication(),超时时间较小。

class Popen(subprocess.Popen):
    def communicate(self, input=None, timeout=None):
        if timeout is None:
            return subprocess.Popen.communicate(self, input)

        if self.stdin:
            # Flush stdio buffer, this might block if user
            # has been writing to .stdin in an uncontrolled
            # fashion.
            self.stdin.flush()
            if not input:
                self.stdin.close()

        read_set, write_set = [], []
        stdout = stderr = None

        if self.stdin and input:
            write_set.append(self.stdin)
        if self.stdout:
            read_set.append(self.stdout)
            stdout = []
        if self.stderr:
            read_set.append(self.stderr)
            stderr = []

        input_offset = 0
        deadline = time.time() + timeout

        while read_set or write_set:
            try:
                rlist, wlist, xlist = select.select(read_set, write_set, [], max(0, deadline - time.time()))
            except select.error as ex:
                if ex.args[0] == errno.EINTR:
                    continue
                raise

            if not (rlist or wlist):
                # Just break if timeout
                # Since we do not close stdout/stderr/stdin, we can call
                # communicate() several times reading data by smaller pieces.
                break

            if self.stdin in wlist:
                chunk = input[input_offset:input_offset + subprocess._PIPE_BUF]
                try:
                    bytes_written = os.write(self.stdin.fileno(), chunk)
                except OSError as ex:
                    if ex.errno == errno.EPIPE:
                        self.stdin.close()
                        write_set.remove(self.stdin)
                    else:
                        raise
                else:
                    input_offset += bytes_written
                    if input_offset >= len(input):
                        self.stdin.close()
                        write_set.remove(self.stdin)

            # Read stdout / stderr by 1024 bytes
            for fn, tgt in (
                (self.stdout, stdout),
                (self.stderr, stderr),
            ):
                if fn in rlist:
                    data = os.read(fn.fileno(), 1024)
                    if data == '':
                        fn.close()
                        read_set.remove(fn)
                    tgt.append(data)

        if stdout is not None:
            stdout = ''.join(stdout)
        if stderr is not None:
            stderr = ''.join(stderr)

        return (stdout, stderr)

有一个想法是子类化Popen类并用一些简单的方法装饰器来扩展它。我们叫它ExpirablePopen吧。

from logging import error
from subprocess import Popen
from threading import Event
from threading import Thread


class ExpirablePopen(Popen):

    def __init__(self, *args, **kwargs):
        self.timeout = kwargs.pop('timeout', 0)
        self.timer = None
        self.done = Event()

        Popen.__init__(self, *args, **kwargs)

    def __tkill(self):
        timeout = self.timeout
        if not self.done.wait(timeout):
            error('Terminating process {} by timeout of {} secs.'.format(self.pid, timeout))
            self.kill()

    def expirable(func):
        def wrapper(self, *args, **kwargs):
            # zero timeout means call of parent method
            if self.timeout == 0:
                return func(self, *args, **kwargs)

            # if timer is None, need to start it
            if self.timer is None:
                self.timer = thr = Thread(target=self.__tkill)
                thr.daemon = True
                thr.start()

            result = func(self, *args, **kwargs)
            self.done.set()

            return result
        return wrapper

    wait = expirable(Popen.wait)
    communicate = expirable(Popen.communicate)


if __name__ == '__main__':
    from subprocess import PIPE

    print ExpirablePopen('ssh -T git@bitbucket.org', stdout=PIPE, timeout=1).communicate()