将模块“子进程”与超时一起使用

这是运行任意命令以返回其stdout数据或在非零退出代码上引发异常的Python代码：

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

communicate 用于等待进程退出：

stdoutdata, stderrdata = proc.communicate()

该subprocess模块不支持超时-可以杀死运行时间超过X秒的进程-因此，communicate可能需要永远运行。

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

在Python 3.3+中：

from subprocess import STDOUT, check_output

output = check_output(cmd, stderr=STDOUT, timeout=seconds)

output 是一个字节字符串，其中包含命令的合并标准输出，标准错误数据。

check_output提出CalledProcessError问题文本中指定的非零退出状态，这与proc.communicate()的方法。

我已删除，shell=True因为它经常不必要地使用。如果cmd确实需要，您可以随时将其添加回去。如果添加，shell=True即子进程是否产生了自己的后代；check_output()可以比超时指示晚得多返回，请参阅子进程超时失败。

超时功能可在Python 2.x上通过subprocess323.2+子进程模块的反向端口使用。

我对底层细节了解不多；但是，鉴于python 2.6中的API提供了等待线程并终止进程的能力，那么如何在单独的线程中运行进程呢？

import subprocess, threading

class Command(object):
    def __init__(self, cmd):
        self.cmd = cmd
        self.process = None

    def run(self, timeout):
        def target():
            print 'Thread started'
            self.process = subprocess.Popen(self.cmd, shell=True)
            self.process.communicate()
            print 'Thread finished'

        thread = threading.Thread(target=target)
        thread.start()

        thread.join(timeout)
        if thread.is_alive():
            print 'Terminating process'
            self.process.terminate()
            thread.join()
        print self.process.returncode

command = Command("echo 'Process started'; sleep 2; echo 'Process finished'")
command.run(timeout=3)
command.run(timeout=1)

我的计算机中此代码段的输出为：

Thread started
Process started
Process finished
Thread finished
0
Thread started
Process started
Terminating process
Thread finished
-15

从中可以看出，在第一次执行中，进程正确完成了（返回代码0），而在第二次执行中，进程终止了（返回代码-15）。

我没有在Windows中进行测试；但是，除了更新示例命令外，我认为它应该可以工作，因为我在文档中没有发现任何不支持thread.join或process.terminate的内容。

可以使用threading.Timer类简化jcollado的答案：

import shlex
from subprocess import Popen, PIPE
from threading import Timer

def run(cmd, timeout_sec):
    proc = Popen(shlex.split(cmd), stdout=PIPE, stderr=PIPE)
    timer = Timer(timeout_sec, proc.kill)
    try:
        timer.start()
        stdout, stderr = proc.communicate()
    finally:
        timer.cancel()

# Examples: both take 1 second
run("sleep 1", 5)  # process ends normally at 1 second
run("sleep 5", 1)  # timeout happens at 1 second

如果您使用的是Unix，

import signal
  ...
class Alarm(Exception):
    pass

def alarm_handler(signum, frame):
    raise Alarm

signal.signal(signal.SIGALRM, alarm_handler)
signal.alarm(5*60)  # 5 minutes
try:
    stdoutdata, stderrdata = proc.communicate()
    signal.alarm(0)  # reset the alarm
except Alarm:
    print "Oops, taking too long!"
    # whatever else

这是Alex Martelli作为具有适当过程终止功能的模块的解决方案。其他方法不起作用，因为它们不使用proc.communicate（）。因此，如果您有一个产生大量输出的进程，它将填充其输出缓冲区，然后阻塞直到您从中读取内容。

from os import kill
from signal import alarm, signal, SIGALRM, SIGKILL
from subprocess import PIPE, Popen

def run(args, cwd = None, shell = False, kill_tree = True, timeout = -1, env = None):
    '''
    Run a command with a timeout after which it will be forcibly
    killed.
    '''
    class Alarm(Exception):
        pass
    def alarm_handler(signum, frame):
        raise Alarm
    p = Popen(args, shell = shell, cwd = cwd, stdout = PIPE, stderr = PIPE, env = env)
    if timeout != -1:
        signal(SIGALRM, alarm_handler)
        alarm(timeout)
    try:
        stdout, stderr = p.communicate()
        if timeout != -1:
            alarm(0)
    except Alarm:
        pids = [p.pid]
        if kill_tree:
            pids.extend(get_process_children(p.pid))
        for pid in pids:
            # process might have died before getting to this line
            # so wrap to avoid OSError: no such process
            try: 
                kill(pid, SIGKILL)
            except OSError:
                pass
        return -9, '', ''
    return p.returncode, stdout, stderr

def get_process_children(pid):
    p = Popen('ps --no-headers -o pid --ppid %d' % pid, shell = True,
              stdout = PIPE, stderr = PIPE)
    stdout, stderr = p.communicate()
    return [int(p) for p in stdout.split()]

if __name__ == '__main__':
    print run('find /', shell = True, timeout = 3)
    print run('find', shell = True)

我修改了sussudio答案。现在函数返回：（ ，returncode，stdout，stderr）timeout - stdout和stderr被解码为UTF-8字符串

def kill_proc(proc, timeout):
  timeout["value"] = True
  proc.kill()

def run(cmd, timeout_sec):
  proc = subprocess.Popen(shlex.split(cmd), stdout=subprocess.PIPE, stderr=subprocess.PIPE)
  timeout = {"value": False}
  timer = Timer(timeout_sec, kill_proc, [proc, timeout])
  timer.start()
  stdout, stderr = proc.communicate()
  timer.cancel()
  return proc.returncode, stdout.decode("utf-8"), stderr.decode("utf-8"), timeout["value"]

惊讶没人提到使用 timeout

timeout 5 ping -c 3 somehost

显然，这不适用于每个用例，但是如果您处理的是简单脚本，那么这是很难克服的。

homebrew对于Mac用户，也可以通过coreutils中的gtimeout 使用。

timeout现在由subprocess模块支持call()并communicate()在其中（在Python3.3中）：

import subprocess

subprocess.call("command", timeout=20, shell=True)

这将调用命令并引发异常

subprocess.TimeoutExpired

如果20秒后命令仍未完成。

然后，您可以处理异常以继续执行代码，例如：

try:
    subprocess.call("command", timeout=20, shell=True)
except subprocess.TimeoutExpired:
    # insert code here

希望这可以帮助。

另一种选择是写入临时文件以防止stdout阻塞，而不是需要使用communication（）进行轮询。这对我有用，而其他答案却没有。例如在Windows上。

    outFile =  tempfile.SpooledTemporaryFile() 
    errFile =   tempfile.SpooledTemporaryFile() 
    proc = subprocess.Popen(args, stderr=errFile, stdout=outFile, universal_newlines=False)
    wait_remaining_sec = timeout

    while proc.poll() is None and wait_remaining_sec > 0:
        time.sleep(1)
        wait_remaining_sec -= 1

    if wait_remaining_sec <= 0:
        killProc(proc.pid)
        raise ProcessIncompleteError(proc, timeout)

    # read temp streams from start
    outFile.seek(0);
    errFile.seek(0);
    out = outFile.read()
    err = errFile.read()
    outFile.close()
    errFile.close()

我不知道为什么它不mentionned但是因为Python 3.5，有一个新的subprocess.run通用指令（即意味着取代check_call，check_output......），并且其具有timeout参数也是如此。

subprocess.run（args，*，stdin = None，input = None，stdout = None，stderr = None，shell = False，cwd = None，timeout = None，check = False，encoding = None，errors = None）

Run the command described by args. Wait for command to complete, then return a CompletedProcess instance.

subprocess.TimeoutExpired超时到期时会引发异常。

这是我的解决方案，我正在使用线程和事件：

import subprocess
from threading import Thread, Event

def kill_on_timeout(done, timeout, proc):
    if not done.wait(timeout):
        proc.kill()

def exec_command(command, timeout):

    done = Event()
    proc = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE)

    watcher = Thread(target=kill_on_timeout, args=(done, timeout, proc))
    watcher.daemon = True
    watcher.start()

    data, stderr = proc.communicate()
    done.set()

    return data, stderr, proc.returncode

实际上：

In [2]: exec_command(['sleep', '10'], 5)
Out[2]: ('', '', -9)

In [3]: exec_command(['sleep', '10'], 11)
Out[3]: ('', '', 0)

我使用的解决方案是给shell命令加上时间限制。如果命令花费的时间太长，则时间限制将停止它，并且Popen将有一个由时间限制设置的返回码。如果大于128，则表示时间限制终止了该进程。

另请参阅具有超时和大输出（> 64K）的python子进程

我将带有线程自的解决方案添加jcollado到了我的Python模块easyprocess中。

安装：

pip install easyprocess

例：

from easyprocess import Proc

# shell is not supported!
stdout=Proc('ping localhost').call(timeout=1.5).stdout
print stdout

如果您使用的是python 2，请尝试一下

import subprocess32

try:
    output = subprocess32.check_output(command, shell=True, timeout=3)
except subprocess32.TimeoutExpired as e:
    print e

前置Linux命令timeout不是一个坏的解决方法，它对我有用。

cmd = "timeout 20 "+ cmd
subprocess.Popen(cmd.split(), stdout=subprocess.PIPE, stderr=subprocess.PIPE)
(output, err) = p.communicate()

我已经实现了我可以从其中一些中学到的东西。这在Windows中有效，并且由于这是社区Wiki，因此我想我也将共享我的代码：

class Command(threading.Thread):
    def __init__(self, cmd, outFile, errFile, timeout):
        threading.Thread.__init__(self)
        self.cmd = cmd
        self.process = None
        self.outFile = outFile
        self.errFile = errFile
        self.timed_out = False
        self.timeout = timeout

    def run(self):
        self.process = subprocess.Popen(self.cmd, stdout = self.outFile, \
            stderr = self.errFile)

        while (self.process.poll() is None and self.timeout > 0):
            time.sleep(1)
            self.timeout -= 1

        if not self.timeout > 0:
            self.process.terminate()
            self.timed_out = True
        else:
            self.timed_out = False

然后从另一个类或文件：

        outFile =  tempfile.SpooledTemporaryFile()
        errFile =   tempfile.SpooledTemporaryFile()

        executor = command.Command(c, outFile, errFile, timeout)
        executor.daemon = True
        executor.start()

        executor.join()
        if executor.timed_out:
            out = 'timed out'
        else:
            outFile.seek(0)
            errFile.seek(0)
            out = outFile.read()
            err = errFile.read()

        outFile.close()
        errFile.close()

一旦您了解了* unix中运行全过程的机器，您将轻松找到更简单的解决方案：

考虑这个简单的示例，如何使用select.select（）使超时的communication（）方法（现在几乎在* nix上几乎所有可用）。这也可以用epoll / poll / kqueue编写，但是select.select（）变体可能是一个很好的例子。而且select.select（）的主要限制（速度和最大1024 fds）不适用于您的任务。

这可以在* nix下工作，不创建线程，不使用信号，可以从任何线程（不仅是主线程）启动，并且速度足够快，可以从我的计算机上的stdout（i5 2.3ghz）读取250mb / s的数据。

在通信结束时加入stdout / stderr存在问题。如果您的程序输出很大，可能会导致占用大量内存。但是您可以在较小的超时时间内多次调用communication（）。

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)

您可以使用 select

import subprocess
from datetime import datetime
from select import select

def call_with_timeout(cmd, timeout):
    started = datetime.now()
    sp = subprocess.Popen(cmd, stdout=subprocess.PIPE)
    while True:
        p = select([sp.stdout], [], [], timeout)
        if p[0]:
            p[0][0].read()
        ret = sp.poll()
        if ret is not None:
            return ret
        if (datetime.now()-started).total_seconds() > timeout:
            sp.kill()
            return None

我已经在Windows，Linux和Mac上成功使用killableprocess。如果您使用的是Cygwin Python，则需要OSAF的killableprocess版本，因为否则本机Windows进程将不会被杀死。

尽管我没有广泛研究它，但我在ActiveState上发现的这种装饰器似乎对这种事情很有用。与一起subprocess.Popen(..., close_fds=True)，至少我已经准备好使用Python编写shell脚本了。

如果shell = True，此解决方案将杀死进程树，将参数传递给进程（或不传递参数），具有超时并获取回调的stdout，stderr和进程输出（它将psutil用于kill_proc_tree）。这是基于SO中发布的几种解决方案，包括jcollado的解决方案。在jcollado的回答中张贴对Anson和jradice的评论的回应。已在Windows Srvr 2012和Ubuntu 14.04中测试。请注意，对于Ubuntu，您需要将parent.children（...）调用更改为parent.get_children（...）。

def kill_proc_tree(pid, including_parent=True):
  parent = psutil.Process(pid)
  children = parent.children(recursive=True)
  for child in children:
    child.kill()
  psutil.wait_procs(children, timeout=5)
  if including_parent:
    parent.kill()
    parent.wait(5)

def run_with_timeout(cmd, current_dir, cmd_parms, timeout):
  def target():
    process = subprocess.Popen(cmd, cwd=current_dir, shell=True, stdout=subprocess.PIPE, stdin=subprocess.PIPE, stderr=subprocess.PIPE)

    # wait for the process to terminate
    if (cmd_parms == ""):
      out, err = process.communicate()
    else:
      out, err = process.communicate(cmd_parms)
    errcode = process.returncode

  thread = Thread(target=target)
  thread.start()

  thread.join(timeout)
  if thread.is_alive():
    me = os.getpid()
    kill_proc_tree(me, including_parent=False)
    thread.join()

有一个想法可以继承Popen类并使用一些简单的方法装饰器对其进行扩展。我们称之为ExpirablePopen。

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()

我遇到的问题是，如果花费的时间比给定的超时时间长，我想终止多线程子进程。我想在中设置一个超时Popen()，但是没有用。然后，我意识到这Popen().wait()等于call()，因此我有了在该.wait(timeout=xxx)方法中设置超时的想法，该方法终于奏效了。因此，我通过以下方式解决了问题：

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()

不幸的是，我受雇主披露源代码的非常严格的政策约束，因此我无法提供实际的代码。但按我的喜好，最好的解决方案是创建一个重写的子类Popen.wait()以轮询而不是无限期地等待，并Popen.__init__接受超时参数。完成后，所有其他Popen方法（调用wait）将按预期工作，包括communicate。

https://pypi.python.org/pypi/python-subprocess2提供了子流程模块的扩展，使您可以等待一段时间，否则终止。

因此，要等待10秒钟才能终止进程，否则请终止：

pipe  = subprocess.Popen('...')

timeout =  10

results = pipe.waitOrTerminate(timeout)

这与Windows和UNIX兼容。“结果”是一个字典，它包含“ returnCode”和“ actionTaken”，returnCode是应用程序的返回值（如果必须终止，则为None）。如果该过程正常完成，则显示为“ SUBPROCESS2_PROCESS_COMPLETED”，或者根据执行的操作显示“ SUBPROCESS2_PROCESS_TERMINATED”和SUBPROCESS2_PROCESS_KILLED的掩码（有关详细信息，请参阅文档）

对于python 2.6+，请使用gevent

 from gevent.subprocess import Popen, PIPE, STDOUT

 def call_sys(cmd, timeout):
      p= Popen(cmd, shell=True, stdout=PIPE)
      output, _ = p.communicate(timeout=timeout)
      assert p.returncode == 0, p. returncode
      return output

 call_sys('./t.sh', 2)

 # t.sh example
 sleep 5
 echo done
 exit 1

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

import subprocess, optparse, os, sys, re, datetime, threading, time, glob, shutil, xml.dom.minidom, traceback

class OutputManager:
    def __init__(self, filename, mode, console, logonly):
        self.con = console
        self.logtoconsole = True
        self.logtofile = False

        if filename:
            try:
                self.f = open(filename, mode)
                self.logtofile = True
                if logonly == True:
                    self.logtoconsole = False
            except IOError:
                print (sys.exc_value)
                print ("Switching to console only output...\n")
                self.logtofile = False
                self.logtoconsole = True

    def write(self, data):
        if self.logtoconsole == True:
            self.con.write(data)
        if self.logtofile == True:
            self.f.write(data)
        sys.stdout.flush()

def getTimeString():
        return time.strftime("%Y-%m-%d", time.gmtime())

def runCommand(command):
    '''
    Execute a command in new thread and return the
    stdout and stderr content of it.
    '''
    try:
        Output = subprocess.Popen(command, stdout=subprocess.PIPE, shell=True).communicate()[0]
    except Exception as e:
        print ("runCommand failed :%s" % (command))
        print (str(e))
        sys.stdout.flush()
        return None
    return Output

def GetOs():
    Os = ""
    if sys.platform.startswith('win32'):
        Os = "win"
    elif sys.platform.startswith('linux'):
        Os = "linux"
    elif sys.platform.startswith('darwin'):
        Os = "mac"
    return Os


def check_output(*popenargs, **kwargs):
    try:
        if 'stdout' in kwargs: 
            raise ValueError('stdout argument not allowed, it will be overridden.') 

        # Get start time.
        startTime = datetime.datetime.now()
        timeoutValue=3600

        cmd = popenargs[0]

        if sys.platform.startswith('win32'):
            process = subprocess.Popen( cmd, stdout=subprocess.PIPE, shell=True) 
        elif sys.platform.startswith('linux'):
            process = subprocess.Popen( cmd , stdout=subprocess.PIPE, shell=True ) 
        elif sys.platform.startswith('darwin'):
            process = subprocess.Popen( cmd , stdout=subprocess.PIPE, shell=True ) 

        stdoutdata, stderrdata = process.communicate( timeout = timeoutValue )
        retcode = process.poll()

        ####################################
        # Catch crash error and log it.
        ####################################
        OutputHandle = None
        try:
            if retcode >= 1:
                OutputHandle = OutputManager( 'CrashJob_' + getTimeString() + '.txt', 'a+', sys.stdout, False)
                OutputHandle.write( cmd )
                print (stdoutdata)
                print (stderrdata)
                sys.stdout.flush()
        except Exception as e:
            print (str(e))

    except subprocess.TimeoutExpired:
            ####################################
            # Catch time out error and log it.
            ####################################
            Os = GetOs()
            if Os == 'win':
                killCmd = "taskkill /FI \"IMAGENAME eq {0}\" /T /F"
            elif Os == 'linux':
                killCmd = "pkill {0)"
            elif Os == 'mac':
                # Linux, Mac OS
                killCmd = "killall -KILL {0}"

            runCommand(killCmd.format("java"))
            runCommand(killCmd.format("YouApp"))

            OutputHandle = None
            try:
                OutputHandle = OutputManager( 'KillJob_' + getTimeString() + '.txt', 'a+', sys.stdout, False)
                OutputHandle.write( cmd )
            except Exception as e:
                print (str(e))
    except Exception as e:
            for frame in traceback.extract_tb(sys.exc_info()[2]):
                        fname,lineno,fn,text = frame
                        print "Error in %s on line %d" % (fname, lineno)

只是想写一些简单的东西。

#!/usr/bin/python

from subprocess import Popen, PIPE
import datetime
import time 

popen = Popen(["/bin/sleep", "10"]);
pid = popen.pid
sttime = time.time();
waittime =  3

print "Start time %s"%(sttime)

while True:
    popen.poll();
    time.sleep(1)
    rcode = popen.returncode
    now = time.time();
    if [ rcode is None ]  and  [ now > (sttime + waittime) ] :
        print "Killing it now"
        popen.kill()