MFC r316676:

Use estimated RTT for receive buffer auto resizing instead of timestamps

Relnotes:	Yes
Sponsored by:	Multiplay

1 files changed, 2 insertions, 60 deletions

diff --git a/sys/netinet/tcp_stacks/fastpath.c b/sys/netinet/tcp_stacks/fastpath.c
index 061c811..375a098 100644
--- a/sys/netinet/tcp_stacks/fastpath.c
+++ b/sys/netinet/tcp_stacks/fastpath.c
@@ -390,62 +390,8 @@ tcp_do_fastnewdata(struct mbuf *m, struct tcphdr *th, struct socket *so,
 			  (void *)tcp_saveipgen, &tcp_savetcp, 0);
 #endif
 	TCP_PROBE3(debug__input, tp, th, m);
-	/*
-	 * Automatic sizing of receive socket buffer.  Often the send
-	 * buffer size is not optimally adjusted to the actual network
-	 * conditions at hand (delay bandwidth product).  Setting the
-	 * buffer size too small limits throughput on links with high
-	 * bandwidth and high delay (eg. trans-continental/oceanic links).
-	 *
-	 * On the receive side the socket buffer memory is only rarely
-	 * used to any significant extent.  This allows us to be much
-	 * more aggressive in scaling the receive socket buffer.  For
-	 * the case that the buffer space is actually used to a large
-	 * extent and we run out of kernel memory we can simply drop
-	 * the new segments; TCP on the sender will just retransmit it
-	 * later.  Setting the buffer size too big may only consume too
-	 * much kernel memory if the application doesn't read() from
-	 * the socket or packet loss or reordering makes use of the
-	 * reassembly queue.
-	 *
-	 * 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;
-	 *
-	 * This algorithm does one step 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.
-	 *
-	 * TODO: Only step up if the application is actually serving
-	 * the buffer to better manage the socket buffer resources.
-	 */
-	if (V_tcp_do_autorcvbuf &&
-	    (to->to_flags & TOF_TS) &&
-	    to->to_tsecr &&
-	    (so->so_rcv.sb_flags & SB_AUTOSIZE)) {
-		if (TSTMP_GT(to->to_tsecr, tp->rfbuf_ts) &&
-		    to->to_tsecr - tp->rfbuf_ts < hz) {
-			if (tp->rfbuf_cnt >
-			    (so->so_rcv.sb_hiwat / 8 * 7) &&
-			    so->so_rcv.sb_hiwat <
-			    V_tcp_autorcvbuf_max) {
-				newsize =
-					min(so->so_rcv.sb_hiwat +
-					    V_tcp_autorcvbuf_inc,
-					    V_tcp_autorcvbuf_max);
-			}
-			/* Start over with next RTT. */
-			tp->rfbuf_ts = 0;
-			tp->rfbuf_cnt = 0;
-		} else
-			tp->rfbuf_cnt += tlen;	/* add up */
-	}
+
+	newsize = tcp_autorcvbuf(m, th, so, tp, tlen);
 
 	/* Add data to socket buffer. */
 	SOCKBUF_LOCK(&so->so_rcv);
@@ -520,10 +466,6 @@ tcp_do_slowpath(struct mbuf *m, struct tcphdr *th, struct socket *so,
 		win = 0;
 	tp->rcv_wnd = imax(win, (int)(tp->rcv_adv - tp->rcv_nxt));
 
-	/* Reset receive buffer auto scaling when not in bulk receive mode. */
-	tp->rfbuf_ts = 0;
-	tp->rfbuf_cnt = 0;
-
 	switch (tp->t_state) {
 
 	/*