Linux下多進程避免殭屍進程的方法

首先服務端是這樣的的，使用父進程進行監聽，每當有一個鏈接到來就開啓一個子進程所以程序大概是這個樣子的：

#include <unistd.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <signal.h>
#include <sys/wait.h>


#include <stdlib.h>
#include <stdio.h>
#include <errno.h>
#include <string.h>


//wait(NULL) 只要有一個子進程退出，那麼wait就會返回
//若多個子進程，只能等待一個。


//while (waitpid(-1, NULL, WNOHANG) > 0)
//	;
//WNOHANG 不掛起，如果沒有子進程，會返回-1，從而可以跳出循環，信號函數執行完畢


#define ERR_EXIT(m) \
        do \
        { \
                perror(m); \
                exit(EXIT_FAILURE); \
        } while(0)


ssize_t readn(int fd, void *buf, size_t count)
{
	size_t nleft = count;
	ssize_t nread;
	char *bufp = (char*)buf;


	while (nleft > 0)
	{
		if ((nread = read(fd, bufp, nleft)) < 0)
		{
			if (errno == EINTR)
				continue;
			return -1;
		}
		else if (nread == 0)
			return count - nleft;


		bufp += nread;
		nleft -= nread;
	}


	return count;
}


ssize_t writen(int fd, const void *buf, size_t count)
{
	size_t nleft = count;
	ssize_t nwritten;
	char *bufp = (char*)buf;


	while (nleft > 0)
	{
		if ((nwritten = write(fd, bufp, nleft)) < 0)
		{
			if (errno == EINTR)
				continue;
			return -1;
		}
		else if (nwritten == 0)
			continue;


		bufp += nwritten;
		nleft -= nwritten;
	}


	return count;
}


ssize_t recv_peek(int sockfd, void *buf, size_t len)
{
	while (1)
	{
		int ret = recv(sockfd, buf, len, MSG_PEEK);
		if (ret == -1 && errno == EINTR)
			continue;
		return ret;
	}
}


ssize_t readline(int sockfd, void *buf, size_t maxline)
{
	int ret;
	int nread;
	char *bufp = buf;
	int nleft = maxline;
	while (1)
	{
		ret = recv_peek(sockfd, bufp, nleft);
		if (ret < 0)
			return ret;
		else if (ret == 0)
			return ret;


		nread = ret;
		int i;
		for (i=0; i<nread; i++)
		{
			if (bufp[i] == '\n')
			{
				ret = readn(sockfd, bufp, i+1);
				if (ret != i+1)
					exit(EXIT_FAILURE);


				return ret;
			}
		}


		if (nread > nleft)
			exit(EXIT_FAILURE);


		nleft -= nread;
		ret = readn(sockfd, bufp, nread);
		if (ret != nread)
			exit(EXIT_FAILURE);


		bufp += nread;
	}


	return -1;
}


void echo_srv(int conn)
{
	char recvbuf[1024];
        while (1)
        {
                memset(recvbuf, 0, sizeof(recvbuf));
                int ret = readline(conn, recvbuf, 1024); 
			if (ret == -1)
				ERR_EXIT("readline");
			if (ret == 0)
			{
				printf("client close\n");
				//發現對方關閉時自己也關閉
				close(conn);
				break;
			}
		
                fputs(recvbuf, stdout);
                writen(conn, recvbuf, strlen(recvbuf));
                
             
        }
}

//原因如上
void handle_sigchld(int sig)
{	
	int mypid = 0;
	
	while ( (mypid=waitpid(-1, NULL, WNOHANG)) >0 )
	{
		printf("父進程等待子進程退出:%d \n", mypid);
	}
}
int main(void)
{
    	signal(SIGCHLD, SIG_IGN);


	signal(SIGCHLD, handle_sigchld);
	int listenfd;
	if ((listenfd = socket(PF_INET, SOCK_STREAM, IPPROTO_TCP)) < 0)
		ERR_EXIT("socket");


	struct sockaddr_in servaddr;
	memset(&servaddr, 0, sizeof(servaddr));
	servaddr.sin_family = AF_INET;
	servaddr.sin_port = htons(8001);
	//servaddr.sin_addr.s_addr = htonl(INADDR_ANY);
	servaddr.sin_addr.s_addr = inet_addr("127.0.0.1");
	/*inet_aton("127.0.0.1", &servaddr.sin_addr);*/


	int on = 1;
	if (setsockopt(listenfd, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on)) < 0)
		ERR_EXIT("setsockopt");


	if (bind(listenfd, (struct sockaddr*)&servaddr, sizeof(servaddr)) < 0)
		ERR_EXIT("bind");
		
	if (listen(listenfd, SOMAXCONN) < 0)
		ERR_EXIT("listen");


	struct sockaddr_in peeraddr;
	socklen_t peerlen = sizeof(peeraddr);
	int conn;


	pid_t pid;
	while (1)
	{	//父進程監聽
		if ((conn = accept(listenfd, (struct sockaddr*)&peeraddr, &peerlen)) < 0)
			ERR_EXIT("accept");


		printf("ip=%s port=%d\n", inet_ntoa(peeraddr.sin_addr), ntohs(peeraddr.sin_port));


		pid = fork();
		if (pid == -1)
			ERR_EXIT("fork");
		if (pid == 0)  //子進程與客戶端建立鏈接
		{
			close(listenfd);
			echo_srv(conn);
			exit(EXIT_SUCCESS);
		}
		else{
			close(conn); //父進程也有一份連接，需要關閉		
		}
			
	}
	return 0;
}

順便給出client的代碼，共同複用的函數在上面已經給出下面只貼上主要代碼：

void echo_cli(int sock)
{
	char sendbuf[1024] = {0};
        char recvbuf[1024] = {0};
        while (fgets(sendbuf, sizeof(sendbuf), stdin) != NULL)
        {
                writen(sock, sendbuf, strlen(sendbuf));

                int ret = readline(sock, recvbuf, sizeof(recvbuf));
                if (ret == -1)
                        ERR_EXIT("readline");
                else if (ret == 0)
                {
                        printf("client close\n");
                        break;
                }

                fputs(recvbuf, stdout);
                memset(sendbuf, 0, sizeof(sendbuf));
                memset(recvbuf, 0, sizeof(recvbuf));
        }

        close(sock);
}

int main(void)
{
	int sock;
	if ((sock = socket(PF_INET, SOCK_STREAM, IPPROTO_TCP)) < 0)
		ERR_EXIT("socket");

	struct sockaddr_in servaddr;
	memset(&servaddr, 0, sizeof(servaddr));
	servaddr.sin_family = AF_INET;
	servaddr.sin_port = htons(8001);
	servaddr.sin_addr.s_addr = inet_addr("127.0.0.1");

	if (connect(sock, (struct sockaddr*)&servaddr, sizeof(servaddr)) < 0)
		ERR_EXIT("connect");

	struct sockaddr_in localaddr;
	socklen_t addrlen = sizeof(localaddr);
	if (getsockname(sock, (struct sockaddr*)&localaddr, &addrlen) < 0)
		ERR_EXIT("getsockname");

	printf("ip=%s port=%d\n", inet_ntoa(localaddr.sin_addr), ntohs(localaddr.sin_port));

	echo_cli(sock);

	return 0;
}

以上在client關閉時，server 也可以正常關閉

結語：

建立鏈接很簡單，但是關閉鏈接需要小心，close()函數是引用計數型的，而且socket鏈接也是可以複製的，所以需要小心拷貝複製！！！

不足之處 請務必指出，感謝