# HG changeset patch
# Parent 2309467e4992cab3f95d518ff8e557372b4099b2

diff -r 2309467e4992 sys/netinet/tcp_reass.c
--- a/sys/netinet/tcp_reass.c	Sat Sep 25 01:10:30 2010 +1000
+++ b/sys/netinet/tcp_reass.c	Sat Sep 25 01:40:07 2010 +1000
@@ -92,12 +92,6 @@
     &VNET_NAME(tcp_reass_qsize), 0, &tcp_reass_sysctl_qsize, "I",
     "Global number of TCP Segments currently in Reassembly Queue");
 
-static VNET_DEFINE(int, tcp_reass_maxqlen) = 48;
-#define	V_tcp_reass_maxqlen		VNET(tcp_reass_maxqlen)
-SYSCTL_VNET_INT(_net_inet_tcp_reass, OID_AUTO, maxqlen, CTLFLAG_RW,
-    &VNET_NAME(tcp_reass_maxqlen), 0,
-    "Maximum number of TCP Segments per individual Reassembly Queue");
-
 static VNET_DEFINE(int, tcp_reass_overflows) = 0;
 #define	V_tcp_reass_overflows		VNET(tcp_reass_overflows)
 SYSCTL_VNET_INT(_net_inet_tcp_reass, OID_AUTO, overflows, CTLFLAG_RD,
@@ -197,13 +191,18 @@
 		goto present;
 
 	/*
-	 * Limit the number of segments in the reassembly queue to prevent
-	 * holding on to too many segments (and thus running out of mbufs).
-	 * Make sure to let the missing segment through which caused this
-	 * queue.
+	 * Limit the number of segments that can be queued to reduce the
+	 * potential for mbuf exhaustion. For best performance, we want to be
+	 * able to queue a full window's worth of segments. The size of the
+	 * socket receive buffer determines our advertised window and grows
+	 * automatically when socket buffer autotuning is enabled. Use it as the
+	 * basis for our queue limit.
+	 * Always let the missing segment through which caused this queue.
+	 * NB: Access to the socket buffer is left intentionally unlocked as we
+	 * can tolerate stale information here.
 	 */
 	if (th->th_seq != tp->rcv_nxt &&
-	    tp->t_segqlen >= V_tcp_reass_maxqlen) {
+	    tp->t_segqlen >= (so->so_rcv.sb_hiwat / tp->t_maxseg) + 1) {
 		V_tcp_reass_overflows++;
 		TCPSTAT_INC(tcps_rcvmemdrop);
 		m_freem(m);
@@ -211,6 +210,17 @@
 		return (0);
 	}
 
+	long rxsbspace = sbspace(&so->so_rcv);
+	if (tp->t_segqlen >= (rxsbspace / tp->t_maxseg) + 1) {
+	//if (tp->t_segqlen >= (so->so_rcv.sb_hiwat / tp->t_maxseg) + 1) {
+		printf("tp: %p, t_segqlen: %d, sbspace(so_rcv): %ld, "
+		"so_rcv->sb_hiwat: %d, rcv_wnd: %ld, excess: %ld\n", tp,
+		tp->t_segqlen, rxsbspace / tp->t_maxseg,
+		so->so_rcv.sb_hiwat/tp->t_maxseg,
+		tp->rcv_wnd/tp->t_maxseg, tp->t_segqlen - ((rxsbspace /
+		tp->t_maxseg) + 1));
+	}
+
 	/*
 	 * Allocate a new queue entry. If we can't, or hit the zone limit
 	 * just drop the pkt.