tipc: make replicast a user selectable option

If the bearer carrying multicast messages supports broadcast, those
messages will be sent to all cluster nodes, irrespective of whether
these nodes host any actual destinations socket or not. This is clearly
wasteful if the cluster is large and there are only a few real
destinations for the message being sent.

In this commit we extend the eligibility of the newly introduced
"replicast" transmit option. We now make it possible for a user to
select which method he wants to be used, either as a mandatory setting
via setsockopt(), or as a relative setting where we let the broadcast
layer decide which method to use based on the ratio between cluster
size and the message's actual number of destination nodes.

In the latter case, a sending socket must stick to a previously
selected method until it enters an idle period of at least 5 seconds.
This eliminates the risk of message reordering caused by method change,
i.e., when changes to cluster size or number of destinations would
otherwise mandate a new method to be used.

Reviewed-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 56 insertions, 6 deletions

diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index 672e6ef93cab..7d99029df342 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -54,6 +54,9 @@ const char tipc_bclink_name[] = "broadcast-link";
  * @dest: array keeping number of reachable destinations per bearer
  * @primary_bearer: a bearer having links to all broadcast destinations, if any
  * @bcast_support: indicates if primary bearer, if any, supports broadcast
+ * @rcast_support: indicates if all peer nodes support replicast
+ * @rc_ratio: dest count as percentage of cluster size where send method changes
+ * @bc_threshold: calculated drom rc_ratio; if dests > threshold use broadcast
  */
 struct tipc_bc_base {
 	struct tipc_link *link;
@@ -61,6 +64,9 @@ struct tipc_bc_base {
 	int dests[MAX_BEARERS];
 	int primary_bearer;
 	bool bcast_support;
+	bool rcast_support;
+	int rc_ratio;
+	int bc_threshold;
 };
 
 static struct tipc_bc_base *tipc_bc_base(struct net *net)
@@ -73,6 +79,19 @@ int tipc_bcast_get_mtu(struct net *net)
 	return tipc_link_mtu(tipc_bc_sndlink(net)) - INT_H_SIZE;
 }
 
+void tipc_bcast_disable_rcast(struct net *net)
+{
+	tipc_bc_base(net)->rcast_support = false;
+}
+
+static void tipc_bcbase_calc_bc_threshold(struct net *net)
+{
+	struct tipc_bc_base *bb = tipc_bc_base(net);
+	int cluster_size = tipc_link_bc_peers(tipc_bc_sndlink(net));
+
+	bb->bc_threshold = 1 + (cluster_size * bb->rc_ratio / 100);
+}
+
 /* tipc_bcbase_select_primary(): find a bearer with links to all destinations,
  *                               if any, and make it primary bearer
  */
@@ -175,6 +194,31 @@ static void tipc_bcbase_xmit(struct net *net, struct sk_buff_head *xmitq)
 	__skb_queue_purge(&_xmitq);
 }
 
+static void tipc_bcast_select_xmit_method(struct net *net, int dests,
+					  struct tipc_mc_method *method)
+{
+	struct tipc_bc_base *bb = tipc_bc_base(net);
+	unsigned long exp = method->expires;
+
+	/* Broadcast supported by used bearer/bearers? */
+	if (!bb->bcast_support) {
+		method->rcast = true;
+		return;
+	}
+	/* Any destinations which don't support replicast ? */
+	if (!bb->rcast_support) {
+		method->rcast = false;
+		return;
+	}
+	/* Can current method be changed ? */
+	method->expires = jiffies + TIPC_METHOD_EXPIRE;
+	if (method->mandatory || time_before(jiffies, exp))
+		return;
+
+	/* Determine method to use now */
+	method->rcast = dests <= bb->bc_threshold;
+}
+
 /* tipc_bcast_xmit - broadcast the buffer chain to all external nodes
  * @net: the applicable net namespace
  * @pkts: chain of buffers containing message
@@ -237,16 +281,16 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts,
  *                   and to identified node local sockets
  * @net: the applicable net namespace
  * @pkts: chain of buffers containing message
- * @dests: destination nodes for message. Not consumed.
+ * @method: send method to be used
+ * @dests: destination nodes for message.
  * @cong_link_cnt: returns number of encountered congested destination links
- * @cong_links: returns identities of congested links
  * Consumes buffer chain.
  * Returns 0 if success, otherwise errno
  */
 int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts,
-		    struct tipc_nlist *dests, u16 *cong_link_cnt)
+		    struct tipc_mc_method *method, struct tipc_nlist *dests,
+		    u16 *cong_link_cnt)
 {
-	struct tipc_bc_base *bb = tipc_bc_base(net);
 	struct sk_buff_head inputq, localq;
 	int rc = 0;
 
@@ -258,9 +302,10 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts,
 		rc = -ENOMEM;
 		goto exit;
 	}
-
+	/* Send according to determined transmit method */
 	if (dests->remote) {
-		if (!bb->bcast_support)
+		tipc_bcast_select_xmit_method(net, dests->remote, method);
+		if (method->rcast)
 			rc = tipc_rcast_xmit(net, pkts, dests, cong_link_cnt);
 		else
 			rc = tipc_bcast_xmit(net, pkts, cong_link_cnt);
@@ -269,6 +314,7 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts,
 	if (dests->local)
 		tipc_sk_mcast_rcv(net, &localq, &inputq);
 exit:
+	/* This queue should normally be empty by now */
 	__skb_queue_purge(pkts);
 	return rc;
 }
@@ -377,6 +423,7 @@ void tipc_bcast_add_peer(struct net *net, struct tipc_link *uc_l,
 	tipc_bcast_lock(net);
 	tipc_link_add_bc_peer(snd_l, uc_l, xmitq);
 	tipc_bcbase_select_primary(net);
+	tipc_bcbase_calc_bc_threshold(net);
 	tipc_bcast_unlock(net);
 }
 
@@ -395,6 +442,7 @@ void tipc_bcast_remove_peer(struct net *net, struct tipc_link *rcv_l)
 	tipc_bcast_lock(net);
 	tipc_link_remove_bc_peer(snd_l, rcv_l, &xmitq);
 	tipc_bcbase_select_primary(net);
+	tipc_bcbase_calc_bc_threshold(net);
 	tipc_bcast_unlock(net);
 
 	tipc_bcbase_xmit(net, &xmitq);
@@ -477,6 +525,8 @@ int tipc_bcast_init(struct net *net)
 		goto enomem;
 	bb->link = l;
 	tn->bcl = l;
+	bb->rc_ratio = 25;
+	bb->rcast_support = true;
 	return 0;
 enomem:
 	kfree(bb);