diff mbox

tcp: Lower the initial RTO to 1s as per draft RFC 2988bis-02.

Message ID 1305787669-84634-1-git-send-email-tsunanet@gmail.com
State Changes Requested, archived
Delegated to: David Miller
Headers show

Commit Message

Benoit Sigoure May 19, 2011, 6:47 a.m. UTC 
Draft RFC 2988bis-02 recommends that the initial RTO be lowered
from 3 seconds down to 1 second, and that in case of a timeout
during the TCP 3WHS, the RTO should fallback to 3 seconds when
data transmission begins.

Signed-off-by: Benoit Sigoure <tsunanet@gmail.com>
---

Apologies for the spam, I sent this patch from the wrong address and without
sob'ing it.  I build the Linux kernel in a 15G tmpfs (it's faster this way :D)
and I lost my .git/config after a reboot.

 include/net/tcp.h    |    5 ++++-
 net/ipv4/tcp_input.c |   13 +++++++++----
 2 files changed, 13 insertions(+), 5 deletions(-)

Comments

David Miller May 19, 2011, 8:16 p.m. UTC | #1 
From: Benoit Sigoure <tsunanet@gmail.com>
Date: Wed, 18 May 2011 23:47:49 -0700

> @@ -868,6 +868,11 @@ static void tcp_init_metrics(struct sock *sk)
>  {
>  	struct tcp_sock *tp = tcp_sk(sk);
>  	struct dst_entry *dst = __sk_dst_get(sk);
> +	/* If we had to retransmit anything during the 3WHS, use
> +	 * the initial fallback RTO as per draft RFC 2988bis-02.
> +	 */
> +	int init_rto = inet_csk(sk)->icsk_retransmits ?
> +		TCP_TIMEOUT_INIT_FALLBACK : TCP_TIMEOUT_INIT;

Please do not put comments in the middle of a set of function
local variable declarations.

Also, as mentioned already, icsk_retransmits is not where SYN
retransmissions are counted.

It is stored in the TCP minisocket ->retrans field.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/include/net/tcp.h b/include/net/tcp.h
index cda30ea..274d761 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -122,7 +122,10 @@  extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 #endif
 #define TCP_RTO_MAX	((unsigned)(120*HZ))
 #define TCP_RTO_MIN	((unsigned)(HZ/5))
-#define TCP_TIMEOUT_INIT ((unsigned)(3*HZ))	/* RFC 1122 initial RTO value	*/
+/* The next 2 values come from Draft RFC 2988bis-02. */
+#define TCP_TIMEOUT_INIT ((unsigned)(1*HZ))		/* initial RTO value	*/
+#define TCP_TIMEOUT_INIT_FALLBACK ((unsigned)(3*HZ))	/* initial RTO to fallback to when
+							 * a timeout happens during the 3WHS.	*/
 
 #define TCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ/2U)) /* Maximal interval between probes
 					                 * for local resources.
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bef9f04..a36bc35 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -868,6 +868,11 @@  static void tcp_init_metrics(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct dst_entry *dst = __sk_dst_get(sk);
+	/* If we had to retransmit anything during the 3WHS, use
+	 * the initial fallback RTO as per draft RFC 2988bis-02.
+	 */
+	int init_rto = inet_csk(sk)->icsk_retransmits ?
+		TCP_TIMEOUT_INIT_FALLBACK : TCP_TIMEOUT_INIT;
 
 	if (dst == NULL)
 		goto reset;
@@ -890,7 +895,7 @@  static void tcp_init_metrics(struct sock *sk)
 	if (dst_metric(dst, RTAX_RTT) == 0)
 		goto reset;
 
-	if (!tp->srtt && dst_metric_rtt(dst, RTAX_RTT) < (TCP_TIMEOUT_INIT << 3))
+	if (!tp->srtt && dst_metric_rtt(dst, RTAX_RTT) < (init_rto << 3))
 		goto reset;
 
 	/* Initial rtt is determined from SYN,SYN-ACK.
@@ -916,7 +921,7 @@  static void tcp_init_metrics(struct sock *sk)
 		tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
 	}
 	tcp_set_rto(sk);
-	if (inet_csk(sk)->icsk_rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp) {
+	if (inet_csk(sk)->icsk_rto < init_rto && !tp->rx_opt.saw_tstamp) {
 reset:
 		/* Play conservative. If timestamps are not
 		 * supported, TCP will fail to recalculate correct
@@ -924,8 +929,8 @@  reset:
 		 */
 		if (!tp->rx_opt.saw_tstamp && tp->srtt) {
 			tp->srtt = 0;
-			tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_INIT;
-			inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
+			tp->mdev = tp->mdev_max = tp->rttvar = init_rto;
+			inet_csk(sk)->icsk_rto = init_rto;
 		}
 	}
 	tp->snd_cwnd = tcp_init_cwnd(tp, dst);