From 560c058683bd65b7c2dde1d918b831bca3ee85ef Mon Sep 17 00:00:00 2001
From: Michael Tuexen <tuexen@FreeBSD.org>
Date: Thu, 21 Feb 2019 10:35:32 +0000
Subject: [PATCH] The receive buffer autoscaling for TCP is based on a linear
 growth, which is acceptable in the congestion avoidance phase, but not during
 slow start. The MTU is is also not taken into account. Use a method instead,
 which is based on exponential growth working also in slow start and being
 independent from the MTU.

This is joint work with rrs@.

Reviewed by:		rrs@, Richard Scheffenegger
Sponsored by:		Netflix, Inc.
Differential Revision:	https://reviews.freebsd.org/D18375
---
 sys/netinet/tcp_input.c | 27 ++++++++++++---------------
 1 file changed, 12 insertions(+), 15 deletions(-)

diff --git a/sys/netinet/tcp_input.c b/sys/netinet/tcp_input.c
index b2c4f66da9f0..bedfa856d5d3 100644
--- a/sys/netinet/tcp_input.c
+++ b/sys/netinet/tcp_input.c
@@ -212,11 +212,6 @@ SYSCTL_INT(_net_inet_tcp, OID_AUTO, recvbuf_auto, CTLFLAG_VNET | CTLFLAG_RW,
     &VNET_NAME(tcp_do_autorcvbuf), 0,
     "Enable automatic receive buffer sizing");
 
-VNET_DEFINE(int, tcp_autorcvbuf_inc) = 16*1024;
-SYSCTL_INT(_net_inet_tcp, OID_AUTO, recvbuf_inc, CTLFLAG_VNET | CTLFLAG_RW,
-    &VNET_NAME(tcp_autorcvbuf_inc), 0,
-    "Incrementor step size of automatic receive buffer");
-
 VNET_DEFINE(int, tcp_autorcvbuf_max) = 2*1024*1024;
 SYSCTL_INT(_net_inet_tcp, OID_AUTO, recvbuf_max, CTLFLAG_VNET | CTLFLAG_RW,
     &VNET_NAME(tcp_autorcvbuf_max), 0,
@@ -1449,13 +1444,16 @@ tcp_input(struct mbuf **mp, int *offp, int proto)
  * The criteria to step up the receive buffer one notch are:
  *  1. Application has not set receive buffer size with
  *     SO_RCVBUF. Setting SO_RCVBUF clears SB_AUTOSIZE.
- *  2. the number of bytes received during the time it takes
- *     one timestamp to be reflected back to us (the RTT);
- *  3. received bytes per RTT is within seven eighth of the
- *     current socket buffer size;
- *  4. receive buffer size has not hit maximal automatic size;
+ *  2. the number of bytes received during 1/2 of an sRTT
+ *     is at least 3/8 of the current socket buffer size.
+ *  3. receive buffer size has not hit maximal automatic size;
  *
- * This algorithm does one step per RTT at most and only if
+ * If all of the criteria are met we increaset the socket buffer
+ * by a 1/2 (bounded by the max). This allows us to keep ahead
+ * of slow-start but also makes it so our peer never gets limited
+ * by our rwnd which we then open up causing a burst.
+ *
+ * This algorithm does two steps per RTT at most and only if
  * we receive a bulk stream w/o packet losses or reorderings.
  * Shrinking the buffer during idle times is not necessary as
  * it doesn't consume any memory when idle.
@@ -1472,11 +1470,10 @@ tcp_autorcvbuf(struct mbuf *m, struct tcphdr *th, struct socket *so,
 	if (V_tcp_do_autorcvbuf && (so->so_rcv.sb_flags & SB_AUTOSIZE) &&
 	    tp->t_srtt != 0 && tp->rfbuf_ts != 0 &&
 	    TCP_TS_TO_TICKS(tcp_ts_getticks() - tp->rfbuf_ts) >
-	    (tp->t_srtt >> TCP_RTT_SHIFT)) {
-		if (tp->rfbuf_cnt > (so->so_rcv.sb_hiwat / 8 * 7) &&
+	    ((tp->t_srtt >> TCP_RTT_SHIFT)/2)) {
+		if (tp->rfbuf_cnt > ((so->so_rcv.sb_hiwat / 2)/ 4 * 3) &&
 		    so->so_rcv.sb_hiwat < V_tcp_autorcvbuf_max) {
-			newsize = min(so->so_rcv.sb_hiwat +
-			    V_tcp_autorcvbuf_inc, V_tcp_autorcvbuf_max);
+			newsize = min((so->so_rcv.sb_hiwat + (so->so_rcv.sb_hiwat/2)), V_tcp_autorcvbuf_max);
 		}
 		TCP_PROBE6(receive__autoresize, NULL, tp, m, tp, th, newsize);