BUG/MEDIUM: unix: failed abstract socket binding is retryable
Jan Seda noticed that abstract sockets are incompatible with soft reload,
because the new process cannot bind and immediately fails. This patch marks
the binding as retryable and not fatal so that the new process can try to
bind again after sending a signal to the old process.
Note that this fix is not enough to completely solve the problem, but it
is necessary. This patch should be backported to 1.5.
(cherry picked from commit 3c5efa2b3268f31cffc2c18887010d4bc906a066)
diff --git a/src/proto_uxst.c b/src/proto_uxst.c
index c9a52ff..409c659 100644
--- a/src/proto_uxst.c
+++ b/src/proto_uxst.c
@@ -166,9 +166,11 @@
const char *path;
int ext, ready;
socklen_t ready_len;
-
+ int err;
int ret;
+ err = ERR_NONE;
+
/* ensure we never return garbage */
if (errlen)
*errmsg = 0;
@@ -191,29 +193,34 @@
if (path[0]) {
ret = snprintf(tempname, MAXPATHLEN, "%s.%d.tmp", path, pid);
if (ret < 0 || ret >= MAXPATHLEN) {
+ err |= ERR_FATAL | ERR_ALERT;
msg = "name too long for UNIX socket";
goto err_return;
}
ret = snprintf(backname, MAXPATHLEN, "%s.%d.bak", path, pid);
if (ret < 0 || ret >= MAXPATHLEN) {
+ err |= ERR_FATAL | ERR_ALERT;
msg = "name too long for UNIX socket";
goto err_return;
}
/* 2. clean existing orphaned entries */
if (unlink(tempname) < 0 && errno != ENOENT) {
+ err |= ERR_FATAL | ERR_ALERT;
msg = "error when trying to unlink previous UNIX socket";
goto err_return;
}
if (unlink(backname) < 0 && errno != ENOENT) {
+ err |= ERR_FATAL | ERR_ALERT;
msg = "error when trying to unlink previous UNIX socket";
goto err_return;
}
/* 3. backup existing socket */
if (link(path, backname) < 0 && errno != ENOENT) {
+ err |= ERR_FATAL | ERR_ALERT;
msg = "error when trying to preserve previous UNIX socket";
goto err_return;
}
@@ -231,24 +238,35 @@
fd = socket(PF_UNIX, SOCK_STREAM, 0);
if (fd < 0) {
+ err |= ERR_FATAL | ERR_ALERT;
msg = "cannot create UNIX socket";
goto err_unlink_back;
}
fd_ready:
if (fd >= global.maxsock) {
+ err |= ERR_FATAL | ERR_ALERT;
msg = "socket(): not enough free sockets, raise -n argument";
goto err_unlink_temp;
}
if (fcntl(fd, F_SETFL, O_NONBLOCK) == -1) {
+ err |= ERR_FATAL | ERR_ALERT;
msg = "cannot make UNIX socket non-blocking";
goto err_unlink_temp;
}
if (!ext && bind(fd, (struct sockaddr *)&addr, sizeof(addr)) < 0) {
/* note that bind() creates the socket <tempname> on the file system */
- msg = "cannot bind UNIX socket";
+ if (errno == EADDRINUSE) {
+ /* the old process might still own it, let's retry */
+ err |= ERR_RETRYABLE | ERR_ALERT;
+ msg = "cannot listen to socket";
+ }
+ else {
+ err |= ERR_FATAL | ERR_ALERT;
+ msg = "cannot bind UNIX socket";
+ }
goto err_unlink_temp;
}
@@ -261,6 +279,7 @@
(((listener->bind_conf->ux.uid != -1 || listener->bind_conf->ux.gid != -1) &&
(chown(tempname, listener->bind_conf->ux.uid, listener->bind_conf->ux.gid) == -1)) ||
(listener->bind_conf->ux.mode != 0 && chmod(tempname, listener->bind_conf->ux.mode) == -1))) {
+ err |= ERR_FATAL | ERR_ALERT;
msg = "cannot change UNIX socket ownership";
goto err_unlink_temp;
}
@@ -272,6 +291,7 @@
if (!(ext && ready) && /* only listen if not already done by external process */
listen(fd, listener->backlog ? listener->backlog : listener->maxconn) < 0) {
+ err |= ERR_FATAL | ERR_ALERT;
msg = "cannot listen to UNIX socket";
goto err_unlink_temp;
}
@@ -281,6 +301,7 @@
* backname. Abstract sockets are not renamed.
*/
if (!ext && path[0] && rename(tempname, path) < 0) {
+ err |= ERR_FATAL | ERR_ALERT;
msg = "cannot switch final and temporary UNIX sockets";
goto err_rename;
}
@@ -303,7 +324,8 @@
fd_insert(fd);
fdtab[fd].iocb = listener->proto->accept;
fdtab[fd].owner = listener; /* reference the listener instead of a task */
- return ERR_NONE;
+ return err;
+
err_rename:
ret = rename(backname, path);
if (ret < 0 && errno == ENOENT)
@@ -322,7 +344,7 @@
else
snprintf(errmsg, errlen, "%s [fd %d]", msg, fd);
}
- return ERR_FATAL | ERR_ALERT;
+ return err;
}
/* This function closes the UNIX sockets for the specified listener.