Merge git://git.kvack.org/~bcrl/aio-next

[~andy/linux] / net / ipv4 / tcp_output.c

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 170737a9d56df7d1c3992a64244eea868774abf1..e6bb8256e59f3738280a022f250f6fefd621cb38 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -65,6 +65,9 @@ int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS;
 /* By default, RFC2861 behavior.  */
 int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
 
+unsigned int sysctl_tcp_notsent_lowat __read_mostly = UINT_MAX;
+EXPORT_SYMBOL(sysctl_tcp_notsent_lowat);
+
 static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
                           int push_one, gfp_t gfp);
 
@@ -892,8 +895,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
        skb_orphan(skb);
        skb->sk = sk;
-       skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ?
-                         tcp_wfree : sock_wfree;
+       skb->destructor = tcp_wfree;
        atomic_add(skb->truesize, &sk->sk_wmem_alloc);
 
        /* Build TCP header and checksum it. */
@@ -1628,7 +1630,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
 
        /* If a full-sized TSO skb can be sent, do it. */
        if (limit >= min_t(unsigned int, sk->sk_gso_max_size,
-                          sk->sk_gso_max_segs * tp->mss_cache))
+                          tp->xmit_size_goal_segs * tp->mss_cache))
                goto send_now;
 
        /* Middle in queue won't get any more data, full sendable already? */
@@ -1837,7 +1839,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
        while ((skb = tcp_send_head(sk))) {
                unsigned int limit;
 
-
                tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
                BUG_ON(!tso_segs);
 
@@ -1866,13 +1867,20 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
                                break;
                }
 
-               /* TSQ : sk_wmem_alloc accounts skb truesize,
-                * including skb overhead. But thats OK.
+               /* TCP Small Queues :
+                * Control number of packets in qdisc/devices to two packets / or ~1 ms.
+                * This allows for :
+                *  - better RTT estimation and ACK scheduling
+                *  - faster recovery
+                *  - high rates
                 */
-               if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) {
+               limit = max(skb->truesize, sk->sk_pacing_rate >> 10);
+
+               if (atomic_read(&sk->sk_wmem_alloc) > limit) {
                        set_bit(TSQ_THROTTLED, &tp->tsq_flags);
                        break;
                }
+
                limit = mss_now;
                if (tso_segs > 1 && !tcp_urg_mode(tp))
                        limit = tcp_mss_split_point(sk, skb, mss_now,