From: Pengcheng Yang <yangpc@wangsu.com>
To: edumazet@google.com, ncardwell@google.com, davem@davemloft.net
Cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
Pengcheng Yang <yangpc@wangsu.com>
Subject: [PATCH RESEND net-next v2 3/5] tcp: stretch ACK fixes in Veno prep
Date: Mon, 16 Mar 2020 14:35:09 +0800 [thread overview]
Message-ID: <1584340511-9870-4-git-send-email-yangpc@wangsu.com> (raw)
In-Reply-To: <1584340511-9870-1-git-send-email-yangpc@wangsu.com>
No code logic has been changed in this patch.
Signed-off-by: Pengcheng Yang <yangpc@wangsu.com>
---
net/ipv4/tcp_veno.c | 44 +++++++++++++++++++++++---------------------
1 file changed, 23 insertions(+), 21 deletions(-)
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index 3b36bb1..857491c 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -153,31 +153,33 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
veno->diff = (tp->snd_cwnd << V_PARAM_SHIFT) - target_cwnd;
if (tcp_in_slow_start(tp)) {
- /* Slow start. */
+ /* Slow start. */
tcp_slow_start(tp, acked);
+ goto done;
+ }
+
+ /* Congestion avoidance. */
+ if (veno->diff < beta) {
+ /* In the "non-congestive state", increase cwnd
+ * every rtt.
+ */
+ tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1);
} else {
- /* Congestion avoidance. */
- if (veno->diff < beta) {
- /* In the "non-congestive state", increase cwnd
- * every rtt.
- */
- tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1);
- } else {
- /* In the "congestive state", increase cwnd
- * every other rtt.
- */
- if (tp->snd_cwnd_cnt >= tp->snd_cwnd) {
- if (veno->inc &&
- tp->snd_cwnd < tp->snd_cwnd_clamp) {
- tp->snd_cwnd++;
- veno->inc = 0;
- } else
- veno->inc = 1;
- tp->snd_cwnd_cnt = 0;
+ /* In the "congestive state", increase cwnd
+ * every other rtt.
+ */
+ if (tp->snd_cwnd_cnt >= tp->snd_cwnd) {
+ if (veno->inc &&
+ tp->snd_cwnd < tp->snd_cwnd_clamp) {
+ tp->snd_cwnd++;
+ veno->inc = 0;
} else
- tp->snd_cwnd_cnt++;
- }
+ veno->inc = 1;
+ tp->snd_cwnd_cnt = 0;
+ } else
+ tp->snd_cwnd_cnt++;
}
+done:
if (tp->snd_cwnd < 2)
tp->snd_cwnd = 2;
else if (tp->snd_cwnd > tp->snd_cwnd_clamp)
--
1.8.3.1
next prev parent reply other threads:[~2020-03-16 7:23 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-16 6:35 [PATCH RESEND net-next v2 0/5] tcp: fix stretch ACK bugs in congestion control modules Pengcheng Yang
2020-03-16 6:35 ` [PATCH RESEND net-next v2 1/5] tcp: fix stretch ACK bugs in BIC Pengcheng Yang
2020-03-16 21:19 ` Neal Cardwell
2020-03-16 6:35 ` [PATCH RESEND net-next v2 2/5] tcp: fix stretch ACK bugs in Scalable Pengcheng Yang
2020-03-16 21:25 ` Neal Cardwell
2020-03-16 6:35 ` Pengcheng Yang [this message]
2020-03-16 21:42 ` [PATCH RESEND net-next v2 3/5] tcp: stretch ACK fixes in Veno prep Neal Cardwell
2020-03-16 6:35 ` [PATCH RESEND net-next v2 4/5] tcp: fix stretch ACK bugs in Veno Pengcheng Yang
2020-03-16 21:46 ` Neal Cardwell
2020-03-16 6:35 ` [PATCH RESEND net-next v2 5/5] tcp: fix stretch ACK bugs in Yeah Pengcheng Yang
2020-03-17 1:27 ` [PATCH RESEND net-next v2 0/5] tcp: fix stretch ACK bugs in congestion control modules David Miller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1584340511-9870-4-git-send-email-yangpc@wangsu.com \
--to=yangpc@wangsu.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=ncardwell@google.com \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).