tipc: introduce variable window congestion control

We introduce a simple variable window congestion control for links.
The algorithm is inspired by the Reno algorithm, covering both 'slow
start', 'congestion avoidance', and 'fast recovery' modes.

- We introduce hard lower and upper window limits per link, still
  different and configurable per bearer type.

- We introduce a 'slow start theshold' variable, initially set to
  the maximum window size.

- We let a link start at the minimum congestion window, i.e. in slow
  start mode, and then let is grow rapidly (+1 per rceived ACK) until
  it reaches the slow start threshold and enters congestion avoidance
  mode.

- In congestion avoidance mode we increment the congestion window for
  each window-size number of acked packets, up to a possible maximum
  equal to the configured maximum window.

- For each non-duplicate NACK received, we drop back to fast recovery
  mode, by setting the both the slow start threshold to and the
  congestion window to (current_congestion_window / 2).

- If the timeout handler finds that the transmit queue has not moved
  since the previous timeout, it drops the link back to slow start
  and forces a probe containing the last sent sequence number to the
  sent to the peer, so that this can discover the stale situation.

This change does in reality have effect only on unicast ethernet
transport, as we have seen that there is no room whatsoever for
increasing the window max size for the UDP bearer.
For now, we also choose to keep the limits for the broadcast link
unchanged and equal.

This algorithm seems to give a 50-100% throughput improvement for
messages larger than MTU.
Suggested-by: Xin Long <lucien.xin@gmail.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>

net/tipc/bcast.c

@@ -562,18 +562,18 @@ int tipc_bclink_reset_stats(struct net *net)
 	return 0;
 }
 
-static int tipc_bc_link_set_queue_limits(struct net *net, u32 limit)
+static int tipc_bc_link_set_queue_limits(struct net *net, u32 max_win)
 {
 	struct tipc_link *l = tipc_bc_sndlink(net);
 
 	if (!l)
 		return -ENOPROTOOPT;
-	if (limit < BCLINK_WIN_MIN)
-		limit = BCLINK_WIN_MIN;
-	if (limit > TIPC_MAX_LINK_WIN)
+	if (max_win < BCLINK_WIN_MIN)
+		max_win = BCLINK_WIN_MIN;
+	if (max_win > TIPC_MAX_LINK_WIN)
 		return -EINVAL;
 	tipc_bcast_lock(net);
-	tipc_link_set_queue_limits(l, limit);
+	tipc_link_set_queue_limits(l, BCLINK_WIN_MIN, max_win);
 	tipc_bcast_unlock(net);
 	return 0;
 }
@@ -683,6 +683,7 @@ int tipc_bcast_init(struct net *net)
 	if (!tipc_link_bc_create(net, 0, 0,
 				 FB_MTU,
 				 BCLINK_WIN_DEFAULT,
+				 BCLINK_WIN_DEFAULT,
 				 0,
 				 &bb->inputq,
 				 NULL,

net/tipc/bearer.c

@@ -311,7 +311,8 @@ static int tipc_enable_bearer(struct net *net, const char *name,
 
 	b->identity = bearer_id;
 	b->tolerance = m->tolerance;
-	b->window = m->window;
+	b->min_win = m->min_win;
+	b->max_win = m->max_win;
 	b->domain = disc_domain;
 	b->net_plane = bearer_id + 'A';
 	b->priority = prio;
@@ -796,7 +797,7 @@ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg,
 		goto prop_msg_full;
 	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, bearer->tolerance))
 		goto prop_msg_full;
-	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bearer->window))
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bearer->max_win))
 		goto prop_msg_full;
 	if (bearer->media->type_id == TIPC_MEDIA_TYPE_UDP)
 		if (nla_put_u32(msg->skb, TIPC_NLA_PROP_MTU, bearer->mtu))
@@ -1088,7 +1089,7 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info)
 		if (props[TIPC_NLA_PROP_PRIO])
 			b->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
 		if (props[TIPC_NLA_PROP_WIN])
-			b->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+			b->max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
 		if (props[TIPC_NLA_PROP_MTU]) {
 			if (b->media->type_id != TIPC_MEDIA_TYPE_UDP)
 				return -EINVAL;
@@ -1142,7 +1143,7 @@ static int __tipc_nl_add_media(struct tipc_nl_msg *msg,
 		goto prop_msg_full;
 	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, media->tolerance))
 		goto prop_msg_full;
-	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, media->window))
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, media->max_win))
 		goto prop_msg_full;
 	if (media->type_id == TIPC_MEDIA_TYPE_UDP)
 		if (nla_put_u32(msg->skb, TIPC_NLA_PROP_MTU, media->mtu))
@@ -1275,7 +1276,7 @@ int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info)
 		if (props[TIPC_NLA_PROP_PRIO])
 			m->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
 		if (props[TIPC_NLA_PROP_WIN])
-			m->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+			m->max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
 		if (props[TIPC_NLA_PROP_MTU]) {
 			if (m->type_id != TIPC_MEDIA_TYPE_UDP)
 				return -EINVAL;

net/tipc/bearer.h

@@ -119,7 +119,8 @@ struct tipc_media {
 			char *raw);
 	u32 priority;
 	u32 tolerance;
-	u32 window;
+	u32 min_win;
+	u32 max_win;
 	u32 mtu;
 	u32 type_id;
 	u32 hwaddr_len;
@@ -158,7 +159,8 @@ struct tipc_bearer {
 	struct packet_type pt;
 	struct rcu_head rcu;
 	u32 priority;
-	u32 window;
+	u32 min_win;
+	u32 max_win;
 	u32 tolerance;
 	u32 domain;
 	u32 identity;

net/tipc/eth_media.c

@@ -92,7 +92,8 @@ struct tipc_media eth_media_info = {
 	.raw2addr	= tipc_eth_raw2addr,
 	.priority	= TIPC_DEF_LINK_PRI,
 	.tolerance	= TIPC_DEF_LINK_TOL,
-	.window		= TIPC_DEF_LINK_WIN,
+	.min_win	= TIPC_DEF_LINK_WIN,
+	.max_win	= TIPC_MAX_LINK_WIN,
 	.type_id	= TIPC_MEDIA_TYPE_ETH,
 	.hwaddr_len	= ETH_ALEN,
 	.name		= "eth"

net/tipc/ib_media.c

@@ -42,6 +42,8 @@
 #include "core.h"
 #include "bearer.h"
 
+#define TIPC_MAX_IB_LINK_WIN 500
+
 /* convert InfiniBand address (media address format) media address to string */
 static int tipc_ib_addr2str(struct tipc_media_addr *a, char *str_buf,
 			    int str_size)
@@ -94,7 +96,8 @@ struct tipc_media ib_media_info = {
 	.raw2addr	= tipc_ib_raw2addr,
 	.priority	= TIPC_DEF_LINK_PRI,
 	.tolerance	= TIPC_DEF_LINK_TOL,
-	.window		= TIPC_DEF_LINK_WIN,
+	.min_win	= TIPC_DEF_LINK_WIN,
+	.max_win	= TIPC_MAX_IB_LINK_WIN,
 	.type_id	= TIPC_MEDIA_TYPE_IB,
 	.hwaddr_len	= INFINIBAND_ALEN,
 	.name		= "ib"

net/tipc/link.h

@@ -73,7 +73,7 @@ enum {
 
 bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
 		      int tolerance, char net_plane, u32 mtu, int priority,
-		      int window, u32 session, u32 ownnode,
+		      u32 min_win, u32 max_win, u32 session, u32 ownnode,
 		      u32 peer, u8 *peer_id, u16 peer_caps,
 		      struct tipc_link *bc_sndlink,
 		      struct tipc_link *bc_rcvlink,
@@ -81,7 +81,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
 		      struct sk_buff_head *namedq,
 		      struct tipc_link **link);
 bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer,
-			 int mtu, int window, u16 peer_caps,
+			 int mtu, u32 min_win, u32 max_win, u16 peer_caps,
 			 struct sk_buff_head *inputq,
 			 struct sk_buff_head *namedq,
 			 struct tipc_link *bc_sndlink,
@@ -115,7 +115,8 @@ char *tipc_link_name_ext(struct tipc_link *l, char *buf);
 u32 tipc_link_state(struct tipc_link *l);
 char tipc_link_plane(struct tipc_link *l);
 int tipc_link_prio(struct tipc_link *l);
-int tipc_link_window(struct tipc_link *l);
+int tipc_link_min_win(struct tipc_link *l);
+int tipc_link_max_win(struct tipc_link *l);
 void tipc_link_update_caps(struct tipc_link *l, u16 capabilities);
 bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr);
 unsigned long tipc_link_tolerance(struct tipc_link *l);
@@ -124,7 +125,7 @@ void tipc_link_set_tolerance(struct tipc_link *l, u32 tol,
 void tipc_link_set_prio(struct tipc_link *l, u32 prio,
 			struct sk_buff_head *xmitq);
 void tipc_link_set_abort_limit(struct tipc_link *l, u32 limit);
-void tipc_link_set_queue_limits(struct tipc_link *l, u32 window);
+void tipc_link_set_queue_limits(struct tipc_link *l, u32 min_win, u32 max_win);
 int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg,
 		       struct tipc_link *link, int nlflags);
 int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]);

net/tipc/node.c

@@ -1139,7 +1139,8 @@ void tipc_node_check_dest(struct net *net, u32 addr,
 		snd_l = tipc_bc_sndlink(net);
 		if (!tipc_link_bc_create(net, tipc_own_addr(net),
 					 addr, U16_MAX,
-					 tipc_link_window(snd_l),
+					 tipc_link_min_win(snd_l),
+					 tipc_link_max_win(snd_l),
 					 n->capabilities,
 					 &n->bc_entry.inputq1,
 					 &n->bc_entry.namedq, snd_l,
@@ -1233,7 +1234,7 @@ void tipc_node_check_dest(struct net *net, u32 addr,
 		get_random_bytes(&session, sizeof(u16));
 		if (!tipc_link_create(net, if_name, b->identity, b->tolerance,
 				      b->net_plane, b->mtu, b->priority,
-				      b->window, session,
+				      b->min_win, b->max_win, session,
 				      tipc_own_addr(net), addr, peer_id,
 				      n->capabilities,
 				      tipc_bc_sndlink(n->net), n->bc_entry.link,
@@ -2360,8 +2361,7 @@ int tipc_nl_node_set_link(struct sk_buff *skb, struct genl_info *info)
 	if (attrs[TIPC_NLA_LINK_PROP]) {
 		struct nlattr *props[TIPC_NLA_PROP_MAX + 1];
 
-		err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_LINK_PROP],
-					      props);
+		err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_LINK_PROP], props);
 		if (err) {
 			res = err;
 			goto out;
@@ -2380,10 +2380,12 @@ int tipc_nl_node_set_link(struct sk_buff *skb, struct genl_info *info)
 			tipc_link_set_prio(link, prio, &xmitq);
 		}
 		if (props[TIPC_NLA_PROP_WIN]) {
-			u32 win;
+			u32 max_win;
 
-			win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
-			tipc_link_set_queue_limits(link, win);
+			max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+			tipc_link_set_queue_limits(link,
+						   tipc_link_min_win(link),
+						   max_win);
 		}
 	}
 

net/tipc/udp_media.c

@@ -828,7 +828,8 @@ struct tipc_media udp_media_info = {
 	.msg2addr	= tipc_udp_msg2addr,
 	.priority	= TIPC_DEF_LINK_PRI,
 	.tolerance	= TIPC_DEF_LINK_TOL,
-	.window		= TIPC_DEF_LINK_WIN,
+	.min_win	= TIPC_DEF_LINK_WIN,
+	.max_win	= TIPC_DEF_LINK_WIN,
 	.mtu		= TIPC_DEF_LINK_UDP_MTU,
 	.type_id	= TIPC_MEDIA_TYPE_UDP,
 	.hwaddr_len	= 0,