diff mbox series

[net-next,2/3] tcp: more efficient RACK loss detection

Message ID 20171004200000.39257-3-ycheng@google.com
State Accepted, archived
Delegated to: David Miller
Headers show
Series tcp: improving RACK cpu performance | expand

Commit Message

Yuchung Cheng Oct. 4, 2017, 7:59 p.m. UTC 
Use the new time-ordered list to speed up RACK. The detection
logic is identical. But since the list is chronologically ordered
by skb_mstamp and contains only skbs not yet acked or sacked,
RACK can abort the loop upon hitting skbs that were sent more
recently. On YouTube servers this patch reduces the iterations on
write queue by 40x. The improvement is even bigger with large
BDP networks.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/ipv4/tcp_recovery.c | 20 +++++---------------
 1 file changed, 5 insertions(+), 15 deletions(-)
diff mbox series

Patch

diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index 449cd914d58e..8aa56caefde8 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -45,7 +45,7 @@  static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2)
 static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb;
+	struct sk_buff *skb, *n;
 	u32 reo_wnd;
 
 	*reo_timeout = 0;
@@ -58,17 +58,10 @@  static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
 	if ((tp->rack.reord || !tp->lost_out) && tcp_min_rtt(tp) != ~0U)
 		reo_wnd = max(tcp_min_rtt(tp) >> 2, reo_wnd);
 
-	tcp_for_write_queue(skb, sk) {
+	list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue,
+				 tcp_tsorted_anchor) {
 		struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
 
-		if (skb == tcp_send_head(sk))
-			break;
-
-		/* Skip ones already (s)acked */
-		if (!after(scb->end_seq, tp->snd_una) ||
-		    scb->sacked & TCPCB_SACKED_ACKED)
-			continue;
-
 		if (tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp,
 					tp->rack.end_seq, scb->end_seq)) {
 			/* Step 3 in draft-cheng-tcpm-rack-00.txt:
@@ -81,6 +74,7 @@  static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
 
 			if (remaining < 0) {
 				tcp_rack_mark_skb_lost(sk, skb);
+				list_del_init(&skb->tcp_tsorted_anchor);
 				continue;
 			}
 
@@ -91,11 +85,7 @@  static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
 
 			/* Record maximum wait time (+1 to avoid 0) */
 			*reo_timeout = max_t(u32, *reo_timeout, 1 + remaining);
-
-		} else if (!(scb->sacked & TCPCB_RETRANS)) {
-			/* Original data are sent sequentially so stop early
-			 * b/c the rest are all sent after rack_sent
-			 */
+		} else {
 			break;
 		}
 	}