summaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp_input.c
diff options
context:
space:
mode:
authorYuchung Cheng <ycheng@google.com>2013-08-21 17:29:23 -0700
committerDavid S. Miller <davem@davemloft.net>2013-08-22 14:39:46 -0700
commit0f7cc9a3c2bd89b15720dbf358e9b9e62af27126 (patch)
tree984571f61086e60bc7bad6d6fb62222299cebd95 /net/ipv4/tcp_input.c
parentbe23ab5131621c0dadacdd72de7c94ab168627ee (diff)
tcp: increase throughput when reordering is high
The stack currently detects reordering and avoid spurious retransmission very well. However the throughput is sub-optimal under high reordering because cwnd is increased only if the data is deliverd in order. I.e., FLAG_DATA_ACKED check in tcp_ack(). The more packet are reordered the worse the throughput is. Therefore when reordering is proven high, cwnd should advance whenever the data is delivered regardless of its ordering. If reordering is low, conservatively advance cwnd only on ordered deliveries in Open state, and retain cwnd in Disordered state (RFC5681). Using netperf on a qdisc setup of 20Mbps BW and random RTT from 45ms to 55ms (for reordering effect). This change increases TCP throughput by 20 - 25% to near bottleneck BW. A special case is the stretched ACK with new SACK and/or ECE mark. For example, a receiver may receive an out of order or ECN packet with unacked data buffered because of LRO or delayed ACK. The principle on such an ACK is to advance cwnd on the cummulative acked part first, then reduce cwnd in tcp_fastretrans_alert(). Signed-off-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/tcp_input.c')
-rw-r--r--net/ipv4/tcp_input.c32
1 files changed, 20 insertions, 12 deletions
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e965cc7b87f..ec492eae0cd 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2485,8 +2485,6 @@ static void tcp_try_to_open(struct sock *sk, int flag, const int prior_unsacked)
if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) {
tcp_try_keep_open(sk);
- if (inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
- tcp_moderate_cwnd(tp);
} else {
tcp_cwnd_reduction(sk, prior_unsacked, 0);
}
@@ -3128,11 +3126,24 @@ static inline bool tcp_ack_is_dubious(const struct sock *sk, const int flag)
inet_csk(sk)->icsk_ca_state != TCP_CA_Open;
}
+/* Decide wheather to run the increase function of congestion control. */
static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag)
{
- const struct tcp_sock *tp = tcp_sk(sk);
- return (!(flag & FLAG_ECE) || tp->snd_cwnd < tp->snd_ssthresh) &&
- !tcp_in_cwnd_reduction(sk);
+ if (tcp_in_cwnd_reduction(sk))
+ return false;
+
+ /* If reordering is high then always grow cwnd whenever data is
+ * delivered regardless of its ordering. Otherwise stay conservative
+ * and only grow cwnd on in-order delivery in Open state, and retain
+ * cwnd in Disordered state (RFC5681). A stretched ACK with
+ * new SACK or ECE mark may first advance cwnd here and later reduce
+ * cwnd in tcp_fastretrans_alert() based on more states.
+ */
+ if (tcp_sk(sk)->reordering > sysctl_tcp_reordering)
+ return flag & FLAG_FORWARD_PROGRESS;
+
+ return inet_csk(sk)->icsk_ca_state == TCP_CA_Open &&
+ flag & FLAG_DATA_ACKED;
}
/* Check that window update is acceptable.
@@ -3352,18 +3363,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, sack_rtt);
acked -= tp->packets_out;
+ /* Advance cwnd if state allows */
+ if (tcp_may_raise_cwnd(sk, flag))
+ tcp_cong_avoid(sk, ack, prior_in_flight);
+
if (tcp_ack_is_dubious(sk, flag)) {
- /* Advance CWND, if state allows this. */
- if ((flag & FLAG_DATA_ACKED) && tcp_may_raise_cwnd(sk, flag))
- tcp_cong_avoid(sk, ack, prior_in_flight);
is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
tcp_fastretrans_alert(sk, acked, prior_unsacked,
is_dupack, flag);
- } else {
- if (flag & FLAG_DATA_ACKED)
- tcp_cong_avoid(sk, ack, prior_in_flight);
}
-
if (tp->tlp_high_seq)
tcp_process_tlp_ack(sk, ack, flag);