c - Unix getaddrinfo C函数启动服务器的用法

Question

我正在用C构建一个客户端服务器应用程序，其源代码取自《 Unix环境高级编程》一书。

在服务器中，它正在执行以下操作：

struct addrinfo hint;
memset(&hint, 0, sizeof(hint));
hint.ai_flags = AI_CANONNAME;
hint.ai_socktype = SOCK_STREAM;
hint.ai_addr = NULL;
hint.ai_next = NULL;
....
if ((n = sysconf(_SC_HOST_NAME_MAX))<0)
{
    n = HOST_NAME_MAX;
}
if((host = malloc(n)) == NULL)
{
    printf("malloc error\n");
    exit(1);
}
if (gethostname(host, n)<0)
{
    printf("gethostname error\n");
    exit(1);
}
...
if((err = getaddrinfo(host, "ruptime", &hint, &ailist))!=0)
{
    syslog(LOG_ERR, "ruptimed: getaddrinfo error %s", gai_strerror(err));
    exit(1);
}
for (aip = ailist; aip!=NULL; aip = aip->ai_next)
{
    if ((sockfd = initserver(SOCK_STREAM, aip->ai_addr, aip->ai_addrlen, QLEN))>=0)
    {
        //printf("starting to serve\n");
        serve(sockfd);
        exit(0);
    }
}

据我了解，函数 getaddrinfo用于在主机上查找运行名为 ruptime且类型为 SOCK_STREAM的服务的套接字地址结构。

尽管在书中未指定，但要工作，我必须在文件 /etc/services/中运行一个新条目，并使用一个未使用的端口并指定名称 ruptime：

ruptime         49152/tcp #ruptime Unix System Programming
ruptime         49152/udp #ruptime Unix System Programming

尽管建议不要使用，但建议在其中还添加UDP部分。

但是它说的文件


  如果在 AI_PASSIVE中指定了 hints.ai_flags标志，并且节点为
   NULL，则返回的套接字地址将适用于
  绑定（2）一个将接受（2）连接的套接字。返回的
  套接字地址将包含“通配符地址”（ INADDR_ANY
  IPv4地址， IN6ADDR_ANY_INIT为IPv6地址）。通配符
  该地址由打算用于以下用途的应用程序（通常是服务器）使用：
  接受主机的任何网络地址上的连接。


因此，从这里以及其他有关SO的讨论中，例如：

hint.ai_flags |= AI_PASSIVE
...
getaddrinfo(NULL, myserviceport, &hint, &aihint)

似乎更合适。

这两种方法到底有什么区别？第二个也在寻找 SOCK_DGM吗？有什么理由在书中选择第一种方法？由于第二种方式是由于我在代码中指定了端口，因此是否可以避免在 /etc/services/中添加新条目？

另一个问题。
我必须将客户端名称传递给客户端。我认为环回（客户端和服务器在同一台计算机上运行）地址可以。相反，主机名类似于 ./client MBPdiPippo.lan。是什么定义了可以使用主机名而不使用回送地址创建连接的事实？是我将 host作为第一个参数传递给服务器中的 getaddrinfo吗？

完整代码

server.c

#include<stdio.h>
#include<stdlib.h>
#include<unistd.h> //_SC_HOST_NAME_MAX
#include<string.h>
#include<netdb.h> //Here are defined AF_INET and the others of the family
#include<syslog.h> //LOG_ERR
#include<errno.h> //errno
#include <sys/types.h>

#include"utilities.h"
#include "error.h"

#define BUFLEN 128
#define QLEN 10

#ifndef HOST_NAME_MAX
#define HOST_NAME_MAX 156
#endif

int initserver(int type, const struct sockaddr *addr, socklen_t alen, int qlen);
void serve(int sockfd);

int main(int argc, char* argv[])
{
    printf("entered main\n");
    struct addrinfo *ailist, *aip, hint;
    int sockfd, err, n;
    char *host;
    if (argc != 1)
    {
        printf("usage: ruptimed\n");
        exit(1);
    }
    if ((n=sysconf(_SC_HOST_NAME_MAX))<0)
    {
        n = HOST_NAME_MAX;
    }
    if((host = malloc(n)) == NULL)
    {
        printf("malloc error\n");
        exit(1);
    }
    if (gethostname(host, n)<0)
    {
        printf("gethostname error\n");
        exit(1);
    }
    printf("host: %s\n", host);
    printf("Daemonizing\n");
    int res = daemonize("ruptimed");
    printf("%d\n", res);
    printf("Daemonized\n");
    memset(&hint, 0, sizeof(hint)); //set to 0 all bytes
    printf("hint initialized\n");
    hint.ai_flags = AI_CANONNAME;
    hint.ai_socktype = SOCK_STREAM;
    hint.ai_canonname = NULL;
    hint.ai_addr = NULL;
    hint.ai_next = NULL;
    printf("getting addresses\n");
    if((err = getaddrinfo(host, "ruptime", &hint, &ailist))!=0)
    {
        printf("error %s\n", gai_strerror(err));
        syslog(LOG_ERR, "ruptimed: getaddrinfo error %s", gai_strerror(err));
        exit(1);
    }
    printf("Got addresses\n");
    for (aip = ailist; aip!=NULL; aip = aip->ai_next)
    {
        if ((sockfd = initserver(SOCK_STREAM, aip->ai_addr, aip->ai_addrlen, QLEN))>=0)
        {
            printf("starting to serve\n");
            serve(sockfd);
            exit(0);
        }
    }
    exit(1);
}

void serve(int sockfd)
{
    int clfd;
    FILE *fp;
    char buf[BUFLEN];
    set_cloexec(sockfd);
    for(;;)
    {
        /*After listen, the socket can receive connect requests. accept
        retrieves a connect request and converts it into a connection.
        The file returned by accept is a socket descriptor connected to the client that
        called connect, haing the same coket type and family type. The original
        soket remains available to receive otherconneion requests. If we don't care
        about client's identity we can set the second (struct sockaddr *addr)
        and third parameter (socklen_t *len) to NULL*/
        if((clfd = accept(sockfd, NULL, NULL))<0)
        {
            /*This generates a log mesage.
            syslog(int priority, const char *fformat,...)
            priority is a combination of facility and level. Levels are ordered from highest to lowest:
            LOG_EMERG: emergency system unusable
            LOG_ALERT: condiotin that must be fied immediately
            LOG_CRIT: critical condition
            LOG_ERR: error condition
            LOG_WARNING
            LOG_NOTICE
            LOG_INFO
            LOG_DEBUG
            format and other arguements are passed to vsprintf function forf formatting.*/
            syslog(LOG_ERR, "ruptimed: accept error: %s", strerror(errno));
            exit(1);
        }
        /* set the FD_CLOEXEC file descriptor flag */
        /*it causes the file descriptor to be automatically and atomically closed
         when any of the exec family function is called*/
        set_cloexec(clfd);
        /**pg. 542 Since a common operation is to create a pipe to another process
        to either read its output or write its input Stdio has provided popen and
        pclose: popen creates pipe, close the unused ends of the pipe,
        forks a child and call exec to execute cmdstr and
        returns a file pointer (connected to std output if "r", to stdin if "w").
        pclose closes the stream, waits for the command to terminate*/
        if ((fp = popen("/usr/bin/uptime", "r")) == NULL)
        {
            /*sprintf copy the string passed as second parameter inside buf*/
            sprintf(buf, "error: %s\n", strerror(errno));
            /*pag 610. send is similar to write. send(int sockfd, const void *buf, size_t nbytes, it flags)*/
            send(clfd, buf, strlen(buf),0);
        }
        else
        {
            /*get data from the pipe that reads created to exec /usr/bin/uptime */
            while(fgets(buf, BUFLEN, fp)!=NULL)
            {
                /* clfd is returned by accept and it is a socket descriptor
                connected to the client that called connect*/
                send(clfd, buf, strlen(buf), 0);
            }
            /*see popen pag. 542*/
            pclose(fp);
        }
        close(clfd);
    }
}


int initserver(int type, const struct sockaddr *addr, socklen_t alen, int qlen)
{
    int fd, err;
    int reuse = 1;
    if ((fd = socket(addr->sa_family, type, 0))<0)
    {
        return (-1);
    }
    if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &reuse, sizeof(int))<0)
    {
        goto errout;
    }
    if(bind(fd, addr, alen)<0)
    {
        goto errout;
    }
    if (type == SOCK_STREAM || type == SOCK_SEQPACKET)
    {
        if(listen(fd, qlen)<0)
        {
            goto errout;
        }
    }
    return fd;
    errout:
        err = errno;
        close (fd);
        errno = err;
        return(-1);
}

utilities.c：包含 demonize和 setcloexec函数。在 daemonize函数中，我没有关闭文件描述符以进行调试。

#include "utilities.h"
#include <stdlib.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <stdio.h>
#include <syslog.h>
#include <sys/time.h>//getrlimit
#include <sys/resource.h>//getrlimit
#include <signal.h> //sigempyset , asigcation (umask?)
#include <sys/resource.h>
#include <fcntl.h> //O_RDWR
#include <stdarg.h>

#include "error.h"
int daemonize(const char *cmd)
{
    int fd0, fd1, fd2;
    unsigned int i;
    pid_t pid;
    struct rlimit       rl;
    struct sigaction    sa;
    /* *Clear file creation mask.*/
    umask(0);
    /* *Get maximum number of file descriptors. */
    if (getrlimit(RLIMIT_NOFILE, &rl) < 0)
    {
        err_quit("%s: can’t get file limit", cmd);
    }
    /* *Become a session leader to lose controlling TTY. */
    if ((pid = fork()) < 0)
    {
        err_quit("%s: can’t fork", cmd);
    }
    else if (pid != 0) /* parent */
    {
        exit(0); //the parent will exit
    }
    setsid();
    /* *Ensure future opens won’t allocate controlling TTYs. */
    sa.sa_handler = SIG_IGN;
    sigemptyset(&sa.sa_mask);
    sa.sa_flags = 0;
    if (sigaction(SIGHUP, &sa, NULL) < 0)
    {
        err_quit("%s: can’t ignore SIGHUP", cmd);
    }
    if ((pid = fork()) < 0)
    {
        err_quit("%s: can’t fork", cmd);
    }
    else if (pid != 0) /* parent */
    {
        exit(0);
    }
    /*
    *Change the current working directory to the root so
    * we won’t prevent file systems from being unmounted.
    */
    if (chdir("/") < 0)
    {
        err_quit("%s: can’t change directory to /", cmd);
    }
    /* Close all open file descriptors. */
    if (rl.rlim_max == RLIM_INFINITY)
    {
        rl.rlim_max = 1024;
    }
    printf("closing file descriptors\n");
    /*for (i = 0; i < rl.rlim_max; i++)
    {
        close(i);
    }*/
    /* *Attach file descriptors 0, 1, and 2 to /dev/null.*/
    //printf not working
    /*printf("closed all file descriptors for daemonizing\n");*/
    /*fd0 = open("/dev/null", O_RDWR);
    fd1 = dup(0);
    fd2 = dup(0);*/
    /* *Initialize the log file. Daemons do not have a controlling terminal so
    they can't write to stderror. We don't want them to write to the console device
    because on many workstations the control device runs a windowing system. They can't
    write on separate files either. A central daemon error-logging facility is required.
    This is the BSD. 3 ways to generate log messages:
    1) kernel routines call the log function. These messages can be read from /dev/klog
    2) Most user processes (daemons) call syslog to generate log messages. This causes
    messages to be sent to the UNIX domain datagram socket /dev/log
    3) A user process on this host or on other host connected to this with TCP/ID
    can send log messages to UDP port 514. Explicit network programmin is required
    (it is not managed by syslog.
    The syslogd daemon reads al three of log messages.

    openlog is optional since if not called, syslog calls it. Also closelog is optional
    openlog(const char *ident, int option, int facility)
    It lets us specify ident that is added to each logmessage. option is a bitmask:
        LOG_CONS tells that if the log message can't be sent to syslogd via UNIX
        domain datagram, the message is written to the console instead.
    facility lets the configuration file specify that messages from different
    facilities are to be handled differently. It can be specified also in the 'priority'
    argument of syslog. LOG_DAEMON is for system deamons
    */
    /*
    openlog(cmd, LOG_CONS, LOG_DAEMON);
    if (fd0 != 0 || fd1 != 1 || fd2 != 2)
    {*/
        /*This generates a log mesage.
        syslog(int priority, const char *fformat,...)
        priority is a combination of facility and level. Levels are ordered from highest to lowest:
        LOG_EMERG: emergency system unusable
        LOG_ALERT: condiotin that must be fied immediately
        LOG_CRIT: critical condition
        LOG_ERR: error condition
        LOG_WARNING
        LOG_NOTICE
        LOG_INFO
        LOG_DEBUG

        format and other arguements are passed to vsprintf function forf formatting.*/
        /*syslog(LOG_ERR, "unexpected file descriptors %d %d %d", fd0, fd1, fd2);
        exit(1);
    }*/
    return 0;
}

/*The function set the FD_CLOEXEC flag of the file descriptor already open that
is passed to as parameter. FD_CLOEXEC causes the file descriptor to be
automatically and atomically closed when any of the exec family function is
called*/
int set_cloexec(int fd)
{
    int val;
    /* retrieve the flags of the file descriptor */
    if((val = fcntl(fd, F_GETFD, 0))<0)
    {
        return -1;
    }
    /* set the FD_CLOEXEC file descriptor flag */
    /*it causes the file descriptor to be automatically and atomically closed
     when any of the exec family function is called*/
    val |= FD_CLOEXEC;
    return (fcntl(fd, F_SETFD, val));
}

我使用的错误功能

/* Fatal error unrelated to a system call.
* Print a message and terminate*/
void err_quit (const char *fmt, ...)
{
    va_list ap;
    va_start (ap, fmt);
    err_doit (0, 0, fmt, ap);
    va_end (ap);
    exit(1);
}

/*Print a message and return to caller.
*Caller specifies "errnoflag"*/
static void err_doit(int errnoflag, int error, const char *fmt, va_list ap)
{
    char buf [MAXLINE];
    vsnprintf (buf, MAXLINE-1, fmt, ap);
    if (errnoflag)
    {
        snprintf (buf+strlen(buf), MAXLINE-strlen(buf)-1, ": %s",
            strerror (error));
    }
    strcat(buf, "\n");
    fflush(stdout); /*in case stdout and stderr are the same*/
    fputs (buf, stderr);
    fflush(NULL); /* flushes all stdio output streams*/
}

Answer 1

首先，是一个顽固的行为。 getaddrinfo()代码应合并到initserver()函数中，并在循环后释放套接字结构的链接列表（使用freeaddrinfo()）。这使代码更具可维护性。您希望将紧密耦合的实现紧密联系在一起。


  这两种方法到底有什么区别？


绑定到通配符地址（即，使用NULL获取适当的套接字描述时，使用AI_PASSIVE节点和getaddrinfo()标志）意味着该套接字作为一组绑定到所有网络接口，而不是特定的网络接口。当您绑定到特定的节点名称时，您将绑定到特定的网络接口。

实际上，这意味着，如果其他网络接口在运行时可用，则内核在将数据包路由到绑定到通配符地址的套接字或从套接字传出路由时将考虑它们。

确实应该由每个系统管理员做出选择，因为在某些情况下，服务（您的应用程序）应侦听所有网络接口上的传入连接，但在其他情况下，服务应侦听特定网络上的传入连接。或仅某些特定接口。典型的情况是一台计算机连接到多个网络。对于服务器，这是令人惊讶的普遍现象。对于实际情况，请参见the Apache web server如何配置。

我个人将重写OP的initServer()函数，使其类似于以下内容：

enum {
    /* TCP=1, UDP=2, IPv4=4, IPv6=8 */
    SERVER_TCPv4 = 5,   /* IPv4 | TCP */
    SERVER_UDPv4 = 6,   /* IPv4 | UDP */
    SERVER_TCPv6 = 9,   /* IPv6 | TCP */
    SERVER_UDPv6 = 10,  /* IPv6 | UDP */
    SERVER_TCP   = 13,  /* Any  | TCP */
    SERVER_UDP   = 14   /* Any  | UDP */
};

int initServer(const char *host, const char *port,
               const int type, const int backlog)
{
    struct addrinfo  hints, *list, *curr;
    const char      *node;
    int              family, socktype, result, fd;

    if (!host || !*host || !strcmp(host, "*"))
        node = NULL;
    else
        node = host;

    switch (type) {
    case SERVER_TCPv4: family = AF_INET;   socktype = SOCK_STREAM; break;
    case SERVER_TCPv6: family = AF_INET6;  socktype = SOCK_STREAM; break;
    case SERVER_TCP:   family = AF_UNSPEC; socktype = SOCK_STREAM; break;
    case SERVER_UDPv4: family = AF_INET;   socktype = SOCK_DGRAM;  break;
    case SERVER_UDPv6: family = AF_INET6;  socktype = SOCK_DGRAM;  break;
    case SERVER_UDP:   family = AF_UNSPEC; socktype = SOCK_DGRAM;  break;
    default:
        fprintf(stderr, "initServer(): Invalid server type.\n");
        return -1;
    }
    memset(&hints, 0, sizeof hints);
    hints.ai_flags = AI_PASSIVE;
    hints.ai_family = family;
    hints.ai_socktype = socktype;
    hints.ai_protocol = 0;
    hints.ai_canonname = NULL;
    hints.ai_addr = NULL;
    hints.ai_next = NULL;
    result = getaddrinfo(node, port, &hints, &list);
    if (result) {
        /* Fail. Output error message to standard error. */
        fprintf(stderr, "initServer(): %s.\n", gai_strerror(result));
        return -1;
    }

    fd = -1;
    for (curr = list; curr != NULL; curr = curr->ai_next) {
        int  reuse = 1;

        fd = socket(curr->ai_family, curr->ai_socktype, curr->ai_protocol);
        if (fd == -1)
            continue;

        if (bind(fd, curr->ai_addr, curr->ai_addrlen) == -1) {
            close(fd);
            fd = -1;
            continue;
        }

        if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR,
                        &reuse, sizeof (int)) == -1) {
            close(fd);
            fd = -1;
            continue;
        }

        if (listen(fd, backlog) == -1) {
            close(fd);
            fd = -1;
            continue;
        }

        break;
    }
    freeaddrinfo(list);
    if (fd == -1) {
        fprintf(stderr, "initServer(): Cannot bind to a valid socket.\n");
        return -1;
    }

    return fd;
}

（注意：代码未经测试，甚至没有经过编译；但是基本逻辑是正确的。如果发现任何问题或错误，请在评论中告知我，以便在必要时进行检查，检查和修复。）

这样，您可以从配置文件中读取 host和 port。如果 host为 "*"，为空或为 NULL，则该函数将尝试绑定到通配符地址。 （顺便说一下，这应该是默认值；如果服务器管理员希望限制为特定的接口，则他们可以提供该接口对应的IP地址或主机名。）

同样，系统管理员可以使用配置文件将 port指定为 services数据库（ getent services）中定义的任何字符串，或指定为十进制数字字符串。在OP的情况下， "49152"和 "ruptime"都可以工作。


  由于我在代码中指定了端口，因此是否可以避免在/ etc / services /中添加新条目？


services数据库（运行 getent services在您的计算机上查看它）仅包含服务名称和TCP（ SOCK_STREAM）和/或UDP（ SOCK_DGRAM）协议的端口号之间的映射。

避免必须将 ruptime 49152/tcp条目添加到服务数据库的唯一方法是将端口指定为十进制数字字符串 "49152"而不是名称 "ruptime"。这会影响服务器和客户端。 （也就是说，即使您的服务器知道ruptime是TCP套接字的端口49152，客户端也不会知道，除非它们在自己的服务数据库中拥有。）

通常，大多数管理员不会费心编辑服务数据库，而使用显式端口号。当您安装了防火墙（以及相关的实用程序，例如fail2ban，即使在工作站和便携式计算机上，我也建议使用该防火墙），如果端口号在服务配置文件中清楚显示，则维护规则变得更加容易。

我会自己使用端口号。


  对于在同一台计算机上运行的客户端，我必须传递主机名。我认为环回地址会起作用。是什么定义了可以使用主机名而不使用回送地址创建连接的事实？是否将主机作为第一个参数传递给服务器中的getaddrinfo？


是。如果将服务绑定到通配符地址，它将响应所有网络接口上的请求，包括回送地址。

如果绑定到特定的主机名，它将仅响应对该特定网络接口的请求。

（这是由OS内核完成的，并且是将网络数据包路由到用户空间应用程序的一部分。）

这也意味着绑定到特定主机名（而不是通配符地址）的，启用了Internet的“适当”服务实际上应该能够侦听多个套接字上的传入连接，而不仅仅是一个。它不一定是绝对必要的，甚至在大多数用例中也不是必需的，但是我可以告诉您，当该服务在跨多个不同网络的计算机上运行时，肯定会派上用场，并且您只想为其中的一些提供服务。幸运的是，您可以使监听套接字成为非阻塞的（使用 fcntl(fd, F_SETFL, O_NONBLOCK) －我还建议在定义 fcntl(fd, F_SETFD, O_CLOEXEC)的系统上使用 O_CLOEXEC，以使监听套接字不会意外地传递给执行外部二进制文件的子进程），并且然后使用 select()或 poll()等待 accept()可用的连接；连接到达时，每个套接字都变得可读。