tipc: enable broadcast retrans via unicast

In some environment, broadcast traffic is suppressed at high rate (i.e.
a kind of bandwidth limit setting). When it is applied, TIPC broadcast
can still run successfully. However, when it comes to a high load, some
packets will be dropped first and TIPC tries to retransmit them but the
packet retransmission is intentionally broadcast too, so making things
worse and not helpful at all.

This commit enables the broadcast retransmission via unicast which only
retransmits packets to the specific peer that has really reported a gap
i.e. not broadcasting to all nodes in the cluster, so will prevent from
being suppressed, and also reduce some overheads on the other peers due
to duplicates, finally improve the overall TIPC broadcast performance.

Note: the functionality can be turned on/off via the sysctl file:

echo 1 > /proc/sys/net/tipc/bc_retruni
echo 0 > /proc/sys/net/tipc/bc_retruni

Default is '0', i.e. the broadcast retransmission still works as usual.

Acked-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 8 insertions, 3 deletions

diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index 3ce690a96ee9..50a16f8bebd9 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -46,6 +46,7 @@
 #define BCLINK_WIN_MIN      32	/* bcast minimum link window size */
 
 const char tipc_bclink_name[] = "broadcast-link";
+unsigned long sysctl_tipc_bc_retruni __read_mostly;
 
 /**
  * struct tipc_bc_base - base structure for keeping broadcast send state
@@ -474,7 +475,7 @@ void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l,
 	__skb_queue_head_init(&xmitq);
 
 	tipc_bcast_lock(net);
-	tipc_link_bc_ack_rcv(l, acked, 0, NULL, &xmitq);
+	tipc_link_bc_ack_rcv(l, acked, 0, NULL, &xmitq, NULL);
 	tipc_bcast_unlock(net);
 
 	tipc_bcbase_xmit(net, &xmitq);
@@ -489,7 +490,8 @@ void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l,
  * RCU is locked, no other locks set
  */
 int tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l,
-			struct tipc_msg *hdr)
+			struct tipc_msg *hdr,
+			struct sk_buff_head *retrq)
 {
 	struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq;
 	struct tipc_gap_ack_blks *ga;
@@ -503,8 +505,11 @@ int tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l,
 		tipc_link_bc_init_rcv(l, hdr);
 	} else if (!msg_bc_ack_invalid(hdr)) {
 		tipc_get_gap_ack_blks(&ga, l, hdr, false);
+		if (!sysctl_tipc_bc_retruni)
+			retrq = &xmitq;
 		rc = tipc_link_bc_ack_rcv(l, msg_bcast_ack(hdr),
-					  msg_bc_gap(hdr), ga, &xmitq);
+					  msg_bc_gap(hdr), ga, &xmitq,
+					  retrq);
 		rc |= tipc_link_bc_sync_rcv(l, hdr, &xmitq);
 	}
 	tipc_bcast_unlock(net);