diff options
authorNeal Cardwell <ncardwell@google.com>2015-09-10 04:54:37 (GMT)
committerDavid S. Miller <davem@davemloft.net>2015-09-10 17:58:33 (GMT)
commit05c5a46d71f621df620fbabbd7758ee1b44575ad (patch)
parent32a844056fd43dda647e1c3c6b9983bdfa04d17d (diff)
tcp: generate CA_EVENT_TX_START on data frames
Issuing a CC TX_START event on control frames like pure ACK is a waste of time, as a CC should not care. Following patch needs this change, as we want CUBIC to properly track idle time at a low cost, with a single TX_START being generated. Yuchung might slightly refine the condition triggering TX_START on a followup patch. Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Cc: Jana Iyengar <jri@google.com> Cc: Stephen Hemminger <stephen@networkplumber.org> Cc: Sangtae Ha <sangtae.ha@gmail.com> Cc: Lawrence Brakmo <lawrence@brakmo.org> Signed-off-by: David S. Miller <davem@davemloft.net>
1 files changed, 3 insertions, 3 deletions
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1188e4f..f9a8a12 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -164,6 +164,9 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
struct inet_connection_sock *icsk = inet_csk(sk);
const u32 now = tcp_time_stamp;
+ if (tcp_packets_in_flight(tp) == 0)
+ tcp_ca_event(sk, CA_EVENT_TX_START);
tp->lsndtime = now;
/* If it is a reply for ato after last received
@@ -940,9 +943,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
tcp_header_size = tcp_options_size + sizeof(struct tcphdr);
- if (tcp_packets_in_flight(tp) == 0)
- tcp_ca_event(sk, CA_EVENT_TX_START);
/* if no packet is in qdisc/device queue, then allow XPS to select
* another queue. We can be called from tcp_tsq_handler()
* which holds one reference to sk_wmem_alloc.

Privacy Policy