dlm: bind connections from known local address when using TCP

A common problem occurs when multiple IP addresses within the same
subnet are assigned to the same NIC.  If we make a connection attempt to
another address on the same subnet as one of those addresses, the
connection attempt will not necessarily be routed from the address we
want.

In the case of the DLM, the other nodes will quickly drop the connection
attempt, causing problems.

This patch makes the DLM bind to the local address it acquired from the
cluster manager when using TCP prior to making a connection, obviating
the need for administrators to "fix" their systems or use clever routing
tricks.

Signed-off-by: Lon Hohberger <lhh@redhat.com>
Signed-off-by: Patrick Caulfield <pcaulfie@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>

diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index e9923ca..5772844 100644 (file)
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -864,7 +864,7 @@ static void sctp_init_assoc(struct connection *con)
 static void tcp_connect_to_sock(struct connection *con)
 {
        int result = -EHOSTUNREACH;
-       struct sockaddr_storage saddr;
+       struct sockaddr_storage saddr, src_addr;
        int addr_len;
        struct socket *sock;
 
@@ -898,6 +898,17 @@ static void tcp_connect_to_sock(struct connection *con)
        con->connect_action = tcp_connect_to_sock;
        add_sock(sock, con);
 
+       /* Bind to our cluster-known address connecting to avoid
+          routing problems */
+       memcpy(&src_addr, dlm_local_addr[0], sizeof(src_addr));
+       make_sockaddr(&src_addr, 0, &addr_len);
+       result = sock->ops->bind(sock, (struct sockaddr *) &src_addr,
+                                addr_len);
+       if (result < 0) {
+               log_print("could not bind for connect: %d", result);
+               /* This *may* not indicate a critical error */
+       }
+
        make_sockaddr(&saddr, dlm_config.ci_tcp_port, &addr_len);
 
        log_print("connecting to %d", con->nodeid);