From 16ad3f4022bb53c7541a0bf0410b32d0231ebef9 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Tue, 10 Dec 2019 00:52:46 +0100 Subject: 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 Acked-by: Ying Xue Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/link.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'net/tipc/link.h') diff --git a/net/tipc/link.h b/net/tipc/link.h index c09e9d49d0a3..d3c1c3fc1659 100644 --- a/net/tipc/link.h +++ b/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[]); -- cgit v1.2.3