From d2e1339f40db753286ca0a92c92a847e08c5d2de Mon Sep 17 00:00:00 2001 From: =?utf8?q?Bendik=20R=C3=B8nning=20Opstad?= Date: Wed, 23 Sep 2015 18:49:53 +0200 Subject: [PATCH] tcp: Fix CWV being too strict on thin streams MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Application limited streams such as thin streams, that transmit small amounts of payload in relatively few packets per RTT, can be prevented from growing the CWND when in congestion avoidance. This leads to increased sojourn times for data segments in streams that often transmit time-dependent data. Currently, a connection is considered CWND limited only after having successfully transmitted at least one packet with new data, while at the same time failing to transmit some unsent data from the output queue because the CWND is full. Applications that produce small amounts of data may be left in a state where it is never considered to be CWND limited, because all unsent data is successfully transmitted each time an incoming ACK opens up for more data to be transmitted in the send window. Fix by always testing whether the CWND is fully used after successful packet transmissions, such that a connection is considered CWND limited whenever the CWND has been filled. This is the correct behavior as specified in RFC2861 (section 3.1). Cc: Andreas Petlund Cc: Carsten Griwodz Cc: Jonas Markussen Cc: Kenneth Klette Jonassen Cc: Mads Johannessen Signed-off-by: Bendik Rønning Opstad Acked-by: Eric Dumazet Tested-by: Eric Dumazet Acked-by: Neal Cardwell Tested-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9e53dd9bfcad..09bb082ca1a7 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1822,7 +1822,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, /* Ok, it looks like it is advisable to defer. */ - if (cong_win < send_win && cong_win < skb->len) + if (cong_win < send_win && cong_win <= skb->len) *is_cwnd_limited = true; return true; @@ -2055,7 +2055,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, cwnd_quota = tcp_cwnd_test(tp, skb); if (!cwnd_quota) { - is_cwnd_limited = true; if (push_one == 2) /* Force out a loss probe pkt. */ cwnd_quota = 1; @@ -2137,6 +2136,7 @@ repair: /* Send one loss probe per tail loss episode. */ if (push_one != 2) tcp_schedule_loss_probe(sk); + is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd); tcp_cwnd_validate(sk, is_cwnd_limited); return false; } -- 2.20.1