当父进程在循环中工作时，如何避免僵尸完成子进程

Question

我正在寻找一个好的解决方案，以避免当父进程仍在工作时出现 ZOMBIE 子进程。例如，父级正在循环中工作并正在检查某些条件。如果条件满足，父进程运行子进程。

现在我编写了简单的 python 脚本：

File main.py:

#!/usr/bin/env python3
# coding=utf-8

import os
import psutil
import subprocess
import time
import signal
import setproctitle


def main():

    python_venv = 'python3'
    print(f"{__file__}  - Run proc 1")
    a1 = [python_venv, 'proc1.py']
    string_do_wywolania_part2 = ['arg1'  , 'arg2']
    a2 = a1 + string_do_wywolania_part2
    p = subprocess.Popen(a2, preexec_fn=os.setpgrp)

    print(f"{__file__}  - Run proc 2")
    a1 = [python_venv, 'proc2.py']
    string_do_wywolania_part2 = ['arg1'  , 'arg2']
    a2 = a1 + string_do_wywolania_part2
    p = subprocess.Popen(a2, preexec_fn=os.setpgrp)

    pid_id = os.getpid()
    ppid_id = os.getppid()
    print(f"{__file__} - pid_id  : {pid_id} - ppid_id  : {ppid_id}")

    parent = psutil.Process(pid_id)
    print(f"{__file__} : parent  : {parent}")

    t = 6
    print(f"{__file__} - I am waiting {t} sec.")
    time.sleep(t)



if __name__ == "__main__":

    "call sub processes"
    setproctitle.setproctitle('python3 - main')
    main()

    while True:

        k = 1
        pid_id = os.getpid()
        parent = psutil.Process(pid_id)
        print()
        for child in parent.children(recursive=True):  # or parent.children() for recursive=False
            print(f'{__file__} - {child}  = {child.status()}')
            k +=1
        time.sleep(5)


    print(f'{__file__} : Finished main')

File proc1.py

#!/usr/bin/env python3
# coding=utf-8
import os
import sys
import time
import setproctitle


if __name__ == "__main__":
    setproctitle.setproctitle('python3 - proc1')
    pid = os.getpid()
    ppid = os.getppid()
    print(f"{__file__} - Process 1 is running")
    print(f"{__file__} - pid  : {pid} - ppid  : {ppid}")
    time.sleep(5)
    print(f"{__file__} : Finished process 1  : {pid}")
    sys.exit(0)

proc2.file:

#!/usr/bin/env python3
# coding=utf-8

import os
import sys
import time
import subprocess
import signal
import setproctitle


if __name__ == "__main__":
    setproctitle.setproctitle('python3 - proc2')
    print(f"{__file__} - Process 2 is running")
    try:
        pid = os.getpid()
        ppid = os.getppid()
        print(f"{__file__} - pid  : {pid} - ppid  : {ppid}")
        print(f"{__file__}  - Run proc 3")

        python_venv = 'python3'
        a1 = [python_venv, 'proc3.py']
        string_do_wywolania_part2 = ['arg1'  , 'arg2']
        a2 = a1 + string_do_wywolania_part2
        p = subprocess.Popen(a2, preexec_fn=os.setpgrp)
        time.sleep(15)
    except Exception as e:
        print(e)

    time.sleep(7)
    print(f"{__file__} : Finished process 2  : {pid}")
    sys.exit(0)

和最后一个 proc3.py

#!/usr/bin/env python3
# coding=utf-8

import os
import sys
import time
import setproctitle


if __name__ == "__main__":
    ""
    setproctitle.setproctitle('python3 - proc3')
    pid = os.getpid()
    ppid = os.getppid()
    print(f"{__file__} - Process 3 is running")
    print(f"{__file__} - pid  : {pid} -  ppid  : {ppid}")
    time.sleep(10)
    print(f"{__file__} : Finished process 3  : {pid}")

    sys.exit(0)

当我运行 python3 main.py 时，我得到如下显示：

main.py  - Run proc 1
main.py  - Run proc 2
main.py - pid_id  : 5696 - ppid_id  : 4763
main.py : parent  : psutil.Process(pid=5696, name='python3 - main', status='running', started='14:26:46')
main.py - I am waiting 6 sec.
proc1.py - Process 1 is running
proc1.py - pid  : 5697 - ppid  : 5696
proc2.py - Process 2 is running
proc2.py - pid  : 5698 - ppid  : 5696
proc2.py  - Run proc 3
proc3.py - Process 3 is running
proc3.py - pid  : 5699 -  ppid  : 5698
proc1.py : Finished process 1  : 5697

main.py - psutil.Process(pid=5697, name='python3 - proc1', status='zombie', started='14:26:46')  = zombie
main.py - psutil.Process(pid=5698, name='python3 - proc2', status='sleeping', started='14:26:46')  = sleeping
main.py - psutil.Process(pid=5699, name='python3 - proc3', status='sleeping', started='14:26:46')  = sleeping
proc3.py : Finished process 3  : 5699

main.py - psutil.Process(pid=5697, name='python3 - proc1', status='zombie', started='14:26:46')  = zombie
main.py - psutil.Process(pid=5698, name='python3 - proc2', status='sleeping', started='14:26:46')  = sleeping
main.py - psutil.Process(pid=5699, name='python3 - proc3', status='zombie', started='14:26:46')  = zombie

main.py - psutil.Process(pid=5697, name='python3 - proc1', status='zombie', started='14:26:46')  = zombie
main.py - psutil.Process(pid=5698, name='python3 - proc2', status='sleeping', started='14:26:46')  = sleeping
main.py - psutil.Process(pid=5699, name='python3 - proc3', status='zombie', started='14:26:46')  = zombie

main.py - psutil.Process(pid=5697, name='python3 - proc1', status='zombie', started='14:26:46')  = zombie
main.py - psutil.Process(pid=5698, name='python3 - proc2', status='sleeping', started='14:26:46')  = sleeping
main.py - psutil.Process(pid=5699, name='python3 - proc3', status='zombie', started='14:26:46')  = zombie
proc2.py : Finished process 2  : 5698

main.py - psutil.Process(pid=5697, name='python3 - proc1', status='zombie', started='14:26:46')  = zombie
main.py - psutil.Process(pid=5698, name='python3 - proc2', status='zombie', started='14:26:46')  = zombie

如您所见，proc3 首先是僵尸但是当他的父进程完成时，proc 3 消失。 但我仍然有 proc1 和 proc2 作为僵尸。

如何调用child的子进程并避免它们在完成后属于僵尸？ 我读到了有关 call、popen 和 preexec_fn 的信息，并且我应该 del subprocess.popen 对象，但我不知道哪一个是正确的。

你能告诉我我该怎么办吗？

编辑：

while True:
     if some_condition:
        p = subprocess.Popen()

        # what to do to avoid a zombie childs

     for proc in processes_list:
        if proc.poll() == 0:
            print(f'--> I am terminate {proc} --> {proc.pid}')
            proc.terminate()
            processes_list.remove(proc)

Answer 1

总结一下：

父进程必须等待子进程的退出状态。如果父进程在等待其子进程之前退出，那么最终会出现僵尸进程。

您已经考虑过拥有一个名为 processes_list< 的 Popen 对象列表/code>

您可以将 Popen.wait 与超时一起使用，例如：

for proc in processes_list:
    try:
        # use Popen.wait or Popen.communicate if using pipes.
        proc.wait(timeout=1)
        # proc.returncode contains the exit code of the child
        # no need to track anymore finished
        processes_list.remove(proc)
    except subprocess.TimeoutExpired as to:
        pass

如果您在编辑的代码中使用 Popen.poll ，那么您应该检查 None code> 这意味着孩子是尚未完成，所以不要将其从列表中删除。您在检查 0 但如果返回代码是其他内容怎么办？

while True:

    if some_condition:
        p = subprocess.Popen()
        processes_list.append(p)


    for proc in processes_list:
        # you can save the return value, although proc.returncode should have it as well
        p = proc.poll()
        # None means child is not finished yet, will poll again next round
        if p is not None:
            # again proc.returncode also contains the return code
            print(f'--> I am terminate {proc} --> {proc.pid}')
            processes_list.remove(proc)

最后，在 proc2 文件上同样适用，您必须等待子进程完成，然后让父进程本身退出。这可以通过 Popen.wait 来实现：

#!/usr/bin/env python3
# coding=utf-8

import os
import sys
import time
import subprocess
import signal
import setproctitle


if __name__ == "__main__":
    setproctitle.setproctitle('python3 - proc2')
    print(f"{__file__} - Process 2 is running")
    try:
        pid = os.getpid()
        ppid = os.getppid()
        print(f"{__file__} - pid  : {pid} - ppid  : {ppid}")
        print(f"{__file__}  - Run proc 3")

        python_venv = 'python3'
        a1 = [python_venv, 'proc3.py']
        string_do_wywolania_part2 = ['arg1'  , 'arg2']
        a2 = a1 + string_do_wywolania_part2
        p = subprocess.Popen(a2, preexec_fn=os.setpgrp)
        # no need to sleep as this does not guarantee that the child is done
        #time.sleep(15)
        # this will block until the child is done.
        # if you use poll here it will most probably result in a zombie. 
        p.wait()
        

        
    except Exception as e:
        print(e)

    time.sleep(7)
    print(f"{__file__} : Finished process 2  : {pid}")
    sys.exit(0)