我试图为connect()提供超时。我四处搜索,发现了几篇与此相关的文章。我编写了我认为应该工作的内容但不幸的是我没有从getsockopt()报告错误。但是当我来到write()时,它失败了,错误是107 - ENOTCONN。
有几点。我在Fedora 23上运行.connect()的文档说它应该返回失败的EINPROGRESS错误,因为连接尚未完成但是我遇到了EAGAIN,所以我把它添加到我的支票中。目前我的套接字服务器在listen()调用中将backlog设置为零。许多调用成功但是那些失败的调用都失败了107 - 我在write()调用中提到的ENOTCONN。
我希望我只是遗漏了一些东西,但到目前为止还无法弄清楚是什么。
int domain_socket_send(const char* socket_name, unsigned char* buffer,
unsigned int length, unsigned int timeout)
{
struct sockaddr_un addr;
int fd = -1;
int result = 0;
// Create socket.
fd = socket(AF_UNIX, SOCK_STREAM, 0);
if (fd == -1)
{
result = -1;
goto done;
}
if (timeout != 0)
{
// Enabled non-blocking.
int flags;
flags = fcntl(fd, F_GETFL);
fcntl(fd, F_SETFL, flags | O_NONBLOCK);
}
// Set socket name.
memset(&addr, 0, sizeof(addr));
addr.sun_family = AF_UNIX;
strncpy(addr.sun_path, socket_name, sizeof(addr.sun_path) - 1);
// Connect.
result = connect(fd, (struct sockaddr*) &addr, sizeof(addr));
if (result == -1)
{
// If some error then we're done.
if ((errno != EINPROGRESS) && (errno != EAGAIN))
goto done;
fd_set write_set;
struct timeval tv;
// Set timeout.
tv.tv_sec = timeout / 1000000;
tv.tv_usec = timeout % 1000000;
unsigned int iterations = 0;
while (1)
{
FD_ZERO(&write_set);
FD_SET(fd, &write_set);
result = select(fd + 1, NULL, &write_set, NULL, &tv);
if (result == -1)
goto done;
else if (result == 0)
{
result = -1;
errno = ETIMEDOUT;
goto done;
}
else
{
if (FD_ISSET(fd, &write_set))
{
socklen_t len;
int socket_error;
len = sizeof(socket_error);
// Get the result of the connect() call.
result = getsockopt(fd, SOL_SOCKET, SO_ERROR,
&socket_error, &len);
if (result == -1)
goto done;
// I think SO_ERROR will be zero for a successful
// result and errno otherwise.
if (socket_error != 0)
{
result = -1;
errno = socket_error;
goto done;
}
// Now that the socket is writable issue another connect.
result = connect(fd, (struct sockaddr*) &addr,
sizeof(addr));
if (result == 0)
{
if (iterations > 1)
{
printf("connect() succeeded on iteration %d\n",
iterations);
}
break;
}
else
{
if ((errno != EAGAIN) && (errno != EINPROGRESS))
{
int err = errno;
printf("second connect() failed, errno = %d\n",
errno);
errno = err;
goto done;
}
iterations++;
}
}
}
}
}
// If we put the socket in non-blocking mode then put it back
// to blocking mode.
if (timeout != 0)
{
// Turn off non-blocking.
int flags;
flags = fcntl(fd, F_GETFL);
fcntl(fd, F_SETFL, flags & ~O_NONBLOCK);
}
// Write buffer.
result = write(fd, buffer, length);
if (result == -1)
{
int err = errno;
printf("write() failed, errno = %d\n", err);
errno = err;
goto done;
}
done:
if (result == -1)
result = errno;
else
result = 0;
if (fd != -1)
{
shutdown(fd, SHUT_RDWR);
close(fd);
}
return result;
}
更新04/05/2016:
我突然想到,也许我需要多次调用connect()直到成功,毕竟这是非阻塞的,而不是async io。就像我在read()遇到EAGAIN后要读取数据时再次调用read()一样。另外,我发现了以下SO问题:
Using select() for non-blocking sockets to connect always returns 1
其中EJP的回答说您需要发出多个connect()&#39。另外,从EJP参考书中可以看出:
它似乎表明您需要发出多个connect()' s。我已修改此问题中的代码段以调用connect()直到成功为止。我可能仍然需要对可能更新传递给select()的超时值进行更改,但这不是我的直接问题。
多次调用connect()似乎解决了我原来的问题,那就是我在调用write()时得到了ENOTCONN,我猜是因为socket没有连接。但是,您可以从代码中看到我跟踪选择循环的次数,直到connect()成功。我已经看到这个数字进入了数千人。这让我担心我在忙碌的等待循环中。为什么套接字可写,即使它不处于connect()成功的状态?调用connect()清除可写状态,并且由于某种原因操作系统再次设置它,或者我是否真的处于忙碌的等待循环中?
谢谢, 尼克
答案 0 :(得分:0)
select()
上的错误处理可能会使用一些清理工作。除非设置了SO_ERROR
,否则您不需要查询except_set
。如果select()
返回> 0然后设置write_set
和/或except_set
,如果未设置except_set
则连接成功。
尝试更像这样的东西:
int domain_socket_send(const char* socket_name, unsigned char* buffer,
unsigned int length, unsigned int timeout)
{
struct sockaddr_un addr;
int fd;
int result;
// Create socket.
fd = socket(AF_UNIX, SOCK_STREAM, 0);
if (fd == -1)
return errno;
if (timeout != 0)
{
// Enabled non-blocking.
int flags = fcntl(fd, F_GETFL);
fcntl(fd, F_SETFL, flags | O_NONBLOCK);
}
// Set socket name.
memset(&addr, 0, sizeof(addr));
addr.sun_family = AF_UNIX;
strncpy(addr.sun_path, socket_name, sizeof(addr.sun_path) - 1);
// Connect.
result = connect(fd, (struct sockaddr*) &addr, sizeof(addr));
if (result == -1)
{
// If some error then we're done.
if ((errno != EINPROGRESS) && (errno != EAGAIN))
goto done;
// Now select() to find out when connect() has finished.
fd_set write_set;
fd_set except_set;
FD_ZERO(&write_set);
FD_ZERO(&write_set);
FD_SET(fd, &write_set);
FD_SET(fd, &except_set);
struct timeval tv;
// Set timeout.
tv.tv_sec = timeout / 1000000;
tv.tv_usec = timeout % 1000000;
result = select(fd + 1, NULL, &write_set, &except_set, &tv);
if (result == -1)
{
goto done;
}
else if (result == 0)
{
result = -1;
errno = ETIMEDOUT;
goto done;
}
else if (FD_ISSET(fd, &except_set))
{
int socket_error;
socklen_t len = sizeof(socket_error);
// Get the result of the connect() call.
result = getsockopt(fd, SOL_SOCKET, SO_ERROR, &socket_error, &len);
if (result != -1)
{
result = -1;
errno = socket_error;
}
goto done;
}
else
{
// connected
}
}
// If we put the socket in non-blocking mode then put it back
// to blocking mode.
if (timeout != 0)
{
int flags = fcntl(fd, F_GETFL);
fcntl(fd, F_SETFL, flags & ~O_NONBLOCK);
}
// Write buffer.
result = write(fd, buffer, length);
done:
if (result == -1)
result = errno;
else
result = 0;
if (fd != -1)
{
shutdown(fd, SHUT_RDWR);
close(fd);
}
return result;
}
答案 1 :(得分:0)
来自http://lxr.free-electrons.com/source/net/unix/af_unix.c:
441 static int unix_writable(const struct sock *sk)
442 {
443 return sk->sk_state != TCP_LISTEN &&
444 (atomic_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf;
445 }
我不确定这些缓冲区正在被比较,但很明显,未检查套接字的连接状态。因此,除非在套接字连接时修改这些缓冲区,否则我的unix套接字将始终标记为可写,因此我无法使用select()来确定非阻塞connect()何时完成。
并基于http://lxr.free-electrons.com/source/net/unix/af_unix.c的此片段:
1206 static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
1207 int addr_len, int flags)
.
.
.
1230 timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);
.
.
.
1271 if (unix_recvq_full(other)) {
1272 err = -EAGAIN;
1273 if (!timeo)
1274 goto out_unlock;
1275
1276 timeo = unix_wait_for_peer(other, timeo);
.
.
.
看起来设置发送超时可能能够超时连接。这也与http://man7.org/linux/man-pages/man7/socket.7.html的SO_SNDTIMEO文档相匹配。
谢谢, 尼克