I try to run a TCP client without a server. The idea is simply to periodically try to connect. For this, the client tries to connect to port 1500 on localhost.
Piece of code:
// Create socket
if ((create_socket=socket (AF_INET, SOCK_STREAM, PF_UNSPEC)) > 0)
printf ("Socket createdn");
address.sin_family = AF_INET;
address.sin_port = htons (1500);
inet_aton (argv[1], &address.sin_addr);
// Connect to server
connect ( create_socket,
(struct sockaddr *) &address,
sizeof (address));
FD_ZERO(&fdset);
FD_SET(create_socket, &fdset);
tv.tv_sec = 2; /* 2 seconds timeout */
tv.tv_usec = 0;
rv = select(create_socket + 1, NULL, &fdset, NULL, &tv);
if (rv == 1)
{
int so_error;
socklen_t len = sizeof so_error;
getsockopt(create_socket, SOL_SOCKET, SO_ERROR, &so_error, &len);
if (so_error == 0)
{
printf ("Connection with server (%s) established n",
inet_ntoa (address.sin_addr));
}
else
{
printf("Error on connect: unsuccessfulln");
close (create_socket);
continue;
}
}
else if (rv == 0)
{
printf("Timeout on connectn");
close (create_socket);
continue;
}
else
{
printf("Error on connectn");
close (create_socket);
continue;
}
I’ve set it up in Ubuntu 18.04 on WSL. There, the code waits on select for the defined timeout of 2 seconds and returns appropriate return values. (0 on timeout, 1 on connect).
The return value of connect is -1 on WSL and VMware.
In Ubuntu 18 (VMware) there is no pause in that line. In any case, even without any server listening on that port, I get immediately a return value of 1.
Why is there this difference?
There is a similar behavior later on in that code:
tv.tv_sec = 2;
tv.tv_usec = 0;
if (setsockopt(create_socket, SOL_SOCKET, SO_RCVTIMEO, (const char*)&tv, sizeof tv) < 0)
{
printf("Error on setsockopt SO_RCVTIMEO");
exit(EXIT_FAILURE);
}
// INNER LOOP: Receive data
do
{
size = recv(create_socket, buffer, BUF-1, 0);
if( size > 0)
{
buffer[size] = '';
printf ("Message received: %sn", buffer);
}
else if (size == -1)
{
// on VMware, errno is 107 if there is no server, but coming to that line was not intended
printf ("Timeoutn");
}
else //
{
printf("Server offlinen");
// GO BACK TO OUTER LOOP and reconnect
break;
}
Here, in WSL the recv takes up to 2 seconds, while waiting for any incoming data. (But only if the aforementioned block (connect, select) indicates a valid connection)
In VMware I directly get the feedback. (even without connection)
Does it simply work on WSL by chance?
The argument contains the server IP and is 127.0.0.1.
lsof shows no connection.
Update 2020-11-18
Here’s the full code as requested by Bodo
#include <iostream>
#include <vector>
#include <string>
#include <sys/types.h>
#include <sys/socket.h>
#include <cstring>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <unistd.h>
#include <fcntl.h>
#define BUF 1024
using namespace std;
int main (int argc, char **argv) {
int create_socket;
char *buffer = (char*)malloc(BUF);
struct sockaddr_in address;
int size;
int rv;
struct timeval tv;
fd_set fdset;
// HERE STARTS THE OUTER LOOP - Connect and restart connection
do
{
// Create socket
if ((create_socket=socket (AF_INET, SOCK_STREAM, PF_UNSPEC)) > 0)
printf ("Socket createdn");
address.sin_family = AF_INET;
address.sin_port = htons (15000);
inet_aton ("127.0.0.1", &address.sin_addr);
// Connect to server
int flags = fcntl(create_socket, F_GETFL, 0);
if (flags == -1) return false;
rv = connect ( create_socket,
(struct sockaddr *) &address,
sizeof (address));
printf ("Connect. rv = %in", rv);
if (rv == -1)
{
switch (errno)
{
case ECONNREFUSED: printf ("errno = %i (ECONNREFUSED)n", errno); break;
default: printf ("errno = %i (ECONNREFUSED)n", errno); break;
}
}
FD_ZERO(&fdset);
FD_SET(create_socket, &fdset);
tv.tv_sec = 2;
tv.tv_usec = 0;
rv = select(create_socket + 1, NULL, &fdset, NULL, &tv);
if (rv == 1)
{
int so_error;
socklen_t len = sizeof so_error;
getsockopt(create_socket, SOL_SOCKET, SO_ERROR, &so_error, &len);
if (so_error == 0)
{
printf ("Connection with server (%s) established n",
inet_ntoa (address.sin_addr));
}
else
{
printf("Error on connect: unsuccessfulln");
close (create_socket);
continue;
}
}
else if (rv == 0)
{
printf("Timeout on connectn");
close (create_socket);
continue;
}
else
{
printf("Error on connectn");
close (create_socket);
continue;
}
if (setsockopt(create_socket, SOL_SOCKET, SO_RCVTIMEO, (const char*)&tv, sizeof tv) < 0)
{
printf("Error on setsockopt SO_RCVTIMEO");
exit(EXIT_FAILURE);
}
// INNER LOOP: Receive data
do
{
size = recv(create_socket, buffer, BUF-1, 0);
if( size > 0)
{
buffer[size] = '';
printf ("Data received: %sn", buffer);
}
else if (size == -1)
{
printf ("Timeoutn");
}
else //
{
printf("Server offlinen");
// GO BACK TO OUTER LOOP and reconnect
break;
}
} while (strcmp (buffer, "quitn") != 0);
close (create_socket);
} while (strcmp (buffer, "quitn") != 0);
return EXIT_SUCCESS;
}
In WSL the output is
Socket created Connect. rv = -1 errno = 111 (ECONNREFUSED)
then nothing for 2 seconds afterwards
Timeout on connect Socket created Connect. rv = -1 errno = 111 (ECONNREFUSED)
and again nothing for 2 seconds …
Output in VMware
Socket created Connect. rv = -1 errno = 111 (ECONNREFUSED) Connection with server (127.0.0.1) established Timeout Timeout Timeout Timeout
Where no timeout is fulfilled.
The idea of timeout has been to try to connect on a regular basis, but not as fast as possible.
Advertisement
Answer
Obviously there is something wrong when errno = 111 (ECONNREFUSED) is followed by Connection with server (127.0.0.1) established.
When connect returns -1 and errno is NOT EINPROGRESS you should not use selectand getsockopt(...SO_ERROR...). According to https://man7.org/linux/man-pages/man2/connect.2.html, this is only documented for EINPROGRESS.
Both on real Linux and WSL you get errno = 111 (ECONNREFUSED) after a failed connect. I consider the timeout in WSL wrong as the error (conection refused) was already reported, so it does not make sense to wait for a result. But as the behavior is not specified, it may be implementation dependent.
If you want to have a delay before the next connection attempt, you should not use select but for example sleep followed by repeating the loop.
I suggest something like this:
rv = connect ( create_socket,
(struct sockaddr *) &address,
sizeof (address));
printf ("Connect. rv = %in", rv);
if (rv == -1)
{
switch (errno)
{
case ECONNREFUSED: printf ("errno = %i (ECONNREFUSED) %sn", errno, strerror(errno)); break;
default: printf ("errno = %i (other) %sn", errno, strerror(errno)); break;
}
if(errno != EINPROGRESS)
{
sleep(10); // chose a suitable delay before next connection attempt
continue;
}
}