rds: If one path needs re-connection, check all and re-connect

In testing with mprds enabled, Oracle Cluster nodes after reboot were
not able to communicate with others nodes and so failed to rejoin
the cluster. Peers with lower IP address initiated connection but the
node could not respond as it choose a different path and could not
initiate a connection as it had a higher IP address.

With this patch, when a node sends out a packet and the selected path
is down, all other paths are also checked and any down paths are
re-connected.

Reviewed-by: Ka-cheong Poon <ka-cheong.poon@oracle.com>
Reviewed-by: David Edmondson <david.edmondson@oracle.com>
Signed-off-by: Somasundaram Krishnasamy <somasundaram.krishnasamy@oracle.com>
Signed-off-by: Rao Shoaib <rao.shoaib@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/rds/connection.c b/net/rds/connection.c
index ed7f2133acc2fb12a5419d0a96ca435dc7e3da78..f2fcab182095cbc39f991a4d2886aa2237aec1c8 100644 (file)
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -905,6 +905,17 @@ void rds_conn_path_connect_if_down(struct rds_conn_path *cp)
 }
 EXPORT_SYMBOL_GPL(rds_conn_path_connect_if_down);
 
+/* Check connectivity of all paths
+ */
+void rds_check_all_paths(struct rds_connection *conn)
+{
+       int i = 0;
+
+       do {
+               rds_conn_path_connect_if_down(&conn->c_path[i]);
+       } while (++i < conn->c_npaths);
+}
+
 void rds_conn_connect_if_down(struct rds_connection *conn)
 {
        WARN_ON(conn->c_trans->t_mp_capable);

diff --git a/net/rds/rds.h b/net/rds/rds.h
index 6019b0c004a9df23fbaafd614c8b03492485b294..106e862996b94d377717745523b74b6db07e6a58 100644 (file)
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -778,6 +778,7 @@ void rds_conn_drop(struct rds_connection *conn);
 void rds_conn_path_drop(struct rds_conn_path *cpath, bool destroy);
 void rds_conn_connect_if_down(struct rds_connection *conn);
 void rds_conn_path_connect_if_down(struct rds_conn_path *cp);
+void rds_check_all_paths(struct rds_connection *conn);
 void rds_for_each_conn_info(struct socket *sock, unsigned int len,
                          struct rds_info_iterator *iter,
                          struct rds_info_lengths *lens,
@@ -822,6 +823,12 @@ rds_conn_path_up(struct rds_conn_path *cp)
        return atomic_read(&cp->cp_state) == RDS_CONN_UP;
 }
 
+static inline int
+rds_conn_path_down(struct rds_conn_path *cp)
+{
+       return atomic_read(&cp->cp_state) == RDS_CONN_DOWN;
+}
+
 static inline int
 rds_conn_up(struct rds_connection *conn)
 {

diff --git a/net/rds/send.c b/net/rds/send.c
index 68e2bdb08fd099fd930d0ea66ae037af6a3ba8d2..9a529a01cdc6a10a13d08efcd32947bf22290849 100644 (file)
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1340,7 +1340,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
                goto out;
        }
 
-       rds_conn_path_connect_if_down(cpath);
+       if (rds_conn_path_down(cpath))
+               rds_check_all_paths(conn);
 
        ret = rds_cong_wait(conn->c_fcong, dport, nonblock, rs);
        if (ret) {