ctdb-tcp: Make error handling for outbound connection consistent

If we can't bind the local end of an outgoing connection then
something has gone wrong.  Retrying is better than failing into a
zombie state.  The interface might come back up and/or the address my
be reconfigured.

While here, do the same thing for the other (potentially transient)
failures.

The unknown address family failure is special but just handle it via a
retry.  Technically it can't happen because the node address parsing
can only return values with address family AF_INET or AF_INET6.

BUG: https://bugzilla.samba.org/show_bug.cgi?id=14274
RN: Retry inter-node TCP connections on more transient failures

Reported-by: 耿纪超 <gengjichao@jd.com>
Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
(cherry picked from commit a40fc709cc972dadb40efbf1394b10fae3cfcc07)

Autobuild-User(v4-11-test): Karolin Seeger <kseeger@samba.org>
Autobuild-Date(v4-11-test): Mon Feb 17 13:13:01 UTC 2020 on sn-devel-184

1 files changed, 17 insertions, 19 deletions

diff --git a/ctdb/tcp/tcp_connect.c b/ctdb/tcp/tcp_connect.c
index a75f35a809e..04897f44249 100644
--- a/ctdb/tcp/tcp_connect.c
+++ b/ctdb/tcp/tcp_connect.c
@@ -183,16 +183,14 @@ void ctdb_tcp_node_connect(struct tevent_context *ev, struct tevent_timer *te,
 	tnode->out_fd = socket(sock_out.sa.sa_family, SOCK_STREAM, IPPROTO_TCP);
 	if (tnode->out_fd == -1) {
 		DBG_ERR("Failed to create socket\n");
-		return;
+		goto failed;
 	}
 
 	ret = set_blocking(tnode->out_fd, false);
 	if (ret != 0) {
 		DBG_ERR("Failed to set socket non-blocking (%s)\n",
 			strerror(errno));
-		close(tnode->out_fd);
-		tnode->out_fd = -1;
-		return;
+		goto failed;
 	}
 
 	set_close_on_exec(tnode->out_fd);
@@ -224,32 +222,22 @@ void ctdb_tcp_node_connect(struct tevent_context *ev, struct tevent_timer *te,
 		sockout_size = sizeof(sock_out.ip6);
 		break;
 	default:
-		DEBUG(DEBUG_ERR, (__location__ " unknown family %u\n",
-			sock_in.sa.sa_family));
-		close(tnode->out_fd);
-		tnode->out_fd = -1;
-		return;
+		DBG_ERR("Unknown address family %u\n", sock_in.sa.sa_family);
+		/* Can't happen to due to address parsing restrictions */
+		goto failed;
 	}
 
 	ret = bind(tnode->out_fd, (struct sockaddr *)&sock_in, sockin_size);
 	if (ret == -1) {
 		DBG_ERR("Failed to bind socket (%s)\n", strerror(errno));
-		close(tnode->out_fd);
-		tnode->out_fd = -1;
-		return;
+		goto failed;
 	}
 
 	ret = connect(tnode->out_fd,
 		      (struct sockaddr *)&sock_out,
 		      sockout_size);
 	if (ret != 0 && errno != EINPROGRESS) {
-		ctdb_tcp_stop_connection(node);
-		tnode->connect_te = tevent_add_timer(ctdb->ev,
-						     tnode,
-						     timeval_current_ofs(1, 0),
-						     ctdb_tcp_node_connect,
-						     node);
-		return;
+		goto failed;
 	}
 
 	/* non-blocking connect - wait for write event */
@@ -268,6 +256,16 @@ void ctdb_tcp_node_connect(struct tevent_context *ev, struct tevent_timer *te,
 					     timeval_current_ofs(1, 0),
 					     ctdb_tcp_node_connect,
 					     node);
+
+	return;
+
+failed:
+	ctdb_tcp_stop_connection(node);
+	tnode->connect_te = tevent_add_timer(ctdb->ev,
+					     tnode,
+					     timeval_current_ofs(1, 0),
+					     ctdb_tcp_node_connect,
+					     node);
 }
 
 /*