wait() returns -1, errno=10 启动 Python 进程后

Question

我有一个在线程上启动 Python 进程的 C 程序。 Python 进程使用 Selenium 并向 FTC 提交了骚扰电话投诉。由于Python内存泄漏，posix_spawn用于保持C程序和Python进程分离。我在管理 Python 流程时遇到问题。

Python 进程的 wait() 正在 returning -1，errno 设置为 10。根据 wait(2) man page 这是一个错误。我相信 10 是 ECHILD。 strerror returns No child processes.

$ ./test.exe
Process started, pid 2730
call_datetime: 2019-04-04 18:07:00
caller_name: PERRYVILLE   MD
caller_number: 4106425608
Wait failed -1, 10

运行 Python 直接使用脚本生成预期的 0 return 代码。

$ python3 ftc.py --caller_name "PERRYVILLE   MD" --caller_number 4106425608 --call_datetime "2019-04-04 18:07:00"
call_datetime: 2019-04-04 18:07:00
caller_name: PERRYVILLE   MD
caller_number: 4106425608
$ echo "$?"
0

我发现了两个类似的问题。第一个位于 Linux system() returns -1, ERRNO = 10 No child processes. There is not enough information in the question and it was closed. The second question is at 。我不认为这个问题适用，因为 SIGCHLD 没有被处理。

为什么 wait 因 ECHILD 而失败？

这是C程序。它调用 Python 脚本然后退出。

等待代码取自 wait(2) man page 示例。

$ cat test.c
#include <stdio.h>
#include <errno.h>
#include <string.h>
#include <stdint.h>
#include <pthread.h>
#include <spawn.h>
#include <sys/types.h>
#include <sys/wait.h>

#define log_error printf
#define log_info printf
extern char **environ;

int main(int argc, char* args[])
{
    char* const cname = "PERRYVILLE   MD";
    char* const cnumber = "4106425608";
    char* const ctime = "2019-04-04 18:07:00";

    char* const arguments[] = {
        "python3",
        "ftc.py",
        "--caller_name", cname,
        "--caller_number", cnumber,
        "--call_datetime", ctime,
        NULL
    };

    pid_t pid;
    int res = posix_spawn(&pid, "/usr/bin/python3", NULL, NULL, arguments, environ);

    if (res != 0) {
        log_error("Process failed %d, %d\n", res, errno);
        goto do_exit;
    } else {
        log_info("Process started, pid %d\n", pid);
    }

    do
    {
        res = waitpid(pid, &res, WUNTRACED | WCONTINUED);
        if (res == -1) {
            log_error("Wait failed %d, %d\n", res, errno);
            goto do_exit;
        }

        if (WIFEXITED(res)) {
            log_info("Process exited, result %d\n", WEXITSTATUS(res));
        //} else if (WIFSIGNALED(res)) {
        //    log_info("Process signaled, result %d\n", WTERMSIG(res));
        } else if (WIFSTOPPED(res)) {
            log_info("Process stopped, result %d\n", WSTOPSIG(res));
        } else if (WIFCONTINUED(res)) {
            log_info("Process continued\n");
        }
    } while (!WIFEXITED(res) /*&& !WIFSIGNALED(res)*/);

do_exit:

    return (int)WEXITSTATUS(res);
}

C代码用gcc -Wall -D_GNU_SOURCE -g3 -O1 -std=c99 -pthread test.c -o test.exe编译。

这里是 Python 脚本的相关部分。它打印脚本参数然后退出。

$ cat ftc.py
#!/usr/bin/env python3

import time
import sys

from selenium import webdriver
from selenium.webdriver.firefox.options import Options

def get_option(argv, option):

    argc = len(argv)
    for i in range(0, argc-1):
        if (argv[i] == option and i+1 < argc):
            return argv[i+1]

    return None

def main():

    caller_name = get_option(sys.argv, "--caller_name")
    caller_number = get_option(sys.argv, "--caller_number")
    call_datetime = get_option(sys.argv, "--call_datetime")

    if caller_name is None:
        sys.exit("caller_name is not available")
    if caller_number is None:
        sys.exit("caller_number is not available")
    if call_datetime is None:
        sys.exit("call_datetime is not available")

    print(f"call_datetime: {str(call_datetime)}")
    print(f"caller_name: {str(caller_name)}")
    print(f"caller_number: {str(caller_number)}")

    sys.exit(0)

if __name__ == "__main__":
    main()

Answer 1

您正在用 waitpid() 中的 return 值覆盖等待状态：

    res = waitpid(pid, &res, WUNTRACED | WCONTINUED);

对 return 值和等待状态使用不同的变量：

    int ret = waitpid(pid, &res, WUNTRACED | WCONTINUED);
    if (ret == -1) {
        log_error("Wait failed %d, %d\n", ret, errno);
        goto do_exit;
    }

wait() returns -1, errno=10 启动 Python 进程后

wait() returns -1, errno=10 after launching Python process

c

python

wait