From: Gavin McCullagh <Gavin.McCullagh@nuim.ie>
To: netdev@vger.kernel.org
Subject: Re: [PATCH/RFC] [v2] TCP: use non-delayed ACK for congestion control RTT
Date: Tue, 18 Dec 2007 20:40:22 +0000 [thread overview]
Message-ID: <20071218204022.GA8936@nuim.ie> (raw)
In-Reply-To: <20071217134425.GD7409@nuim.ie>
The last attempt didn't take account of the situation where a timestamp
wasn't available and tcp_clean_rtx_queue() has to feed both the RTO and the
congestion avoidance. This updated patch stores both RTTs, making the
delayed one available for the RTO and the other (ca_seq_rtt) available for
congestion control.
Signed-off-by: Gavin McCullagh <gavin.mccullagh@nuim.ie>
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 889c893..6fb7989 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2651,6 +2651,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, s32 *seq_rtt_p,
u32 cnt = 0;
u32 reord = tp->packets_out;
s32 seq_rtt = -1;
+ s32 ca_seq_rtt = -1;
ktime_t last_ackt = net_invalid_timestamp();
while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
@@ -2686,13 +2687,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, s32 *seq_rtt_p,
if (sacked & TCPCB_SACKED_RETRANS)
tp->retrans_out -= packets_acked;
flag |= FLAG_RETRANS_DATA_ACKED;
+ ca_seq_rtt = -1;
seq_rtt = -1;
if ((flag & FLAG_DATA_ACKED) ||
(packets_acked > 1))
flag |= FLAG_NONHEAD_RETRANS_ACKED;
} else {
+ ca_seq_rtt = now - scb->when;
if (seq_rtt < 0) {
- seq_rtt = now - scb->when;
+ seq_rtt = ca_seq_rtt;
if (fully_acked)
last_ackt = skb->tstamp;
}
@@ -2709,8 +2712,9 @@ static int tcp_clean_rtx_queue(struct sock *sk, s32 *seq_rtt_p,
!before(end_seq, tp->snd_up))
tp->urg_mode = 0;
} else {
+ ca_seq_rtt = now - scb->when;
if (seq_rtt < 0) {
- seq_rtt = now - scb->when;
+ seq_rtt = ca_seq_rtt;
if (fully_acked)
last_ackt = skb->tstamp;
}
@@ -2772,8 +2776,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, s32 *seq_rtt_p,
net_invalid_timestamp()))
rtt_us = ktime_us_delta(ktime_get_real(),
last_ackt);
- else if (seq_rtt > 0)
- rtt_us = jiffies_to_usecs(seq_rtt);
+ else if (ca_seq_rtt > 0)
+ rtt_us = jiffies_to_usecs(ca_seq_rtt);
}
ca_ops->pkts_acked(sk, pkts_acked, rtt_us);
next prev parent reply other threads:[~2007-12-18 20:40 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-12-17 13:44 [PATCH/RFC] TCP: use non-delayed ACK for congestion control RTT Gavin McCullagh
2007-12-18 20:40 ` Gavin McCullagh [this message]
2007-12-19 10:28 ` [PATCH/RFC] [v2] " Gavin McCullagh
2007-12-19 11:08 ` Ilpo Järvinen
2007-12-19 11:31 ` Gavin McCullagh
2007-12-19 13:30 ` Ilpo Järvinen
2007-12-21 11:14 ` David Miller
2007-12-21 13:31 ` Gavin McCullagh
2007-12-21 14:05 ` David Miller
2007-12-21 14:07 ` Ilpo Järvinen
2007-12-21 14:10 ` Ilpo Järvinen
2007-12-30 1:15 ` [PATCH/RFC] [v3] " Gavin McCullagh
2007-12-30 1:25 ` Gavin McCullagh
2007-12-30 3:09 ` David Miller
2007-12-30 12:20 ` Gavin McCullagh
2007-12-30 3:06 ` David Miller
2007-12-30 9:43 ` Ilpo Järvinen
2007-12-30 12:35 ` Gavin McCullagh
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=20071218204022.GA8936@nuim.ie \
--to=gavin.mccullagh@nuim.ie \
--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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.