[PATCH net-next v2 0/2] minor tail loss probe improvements

[PATCH net-next v2 0/2] minor tail loss probe improvements

[Yuchung Cheng]

This patch series enhance the tail loss probe (TLP) on some error
conditions. When TLP fails to send a probe, it will no longer
extend the RTO. When it fails to send a new packet because of
receiver window limit, it'll try to retransmit the last packet.

Yuchung Cheng (2):
  tcp: don't extend RTO on failed loss probe attempts
  tcp: TLP retransmits last if failed to send new packet

 net/ipv4/tcp_output.c | 41 +++++++++++++++++++++++------------------
 1 file changed, 23 insertions(+), 18 deletions(-)

-- 
2.5.0.276.gf5e568e

[PATCH net-next v2 1/2] tcp: don't extend RTO on failed loss probe attempts

[Yuchung Cheng]

If TLP was unable to send a probe, it extended the RTO to
now + icsk_rto. But extending the RTO makes little sense
if no TLP probe went out. With this commit, instead of
extending the RTO we re-arm it relative to the transmit time
of the write queue head.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Nandita Dukkipati <nanditad@google.com>
---
 net/ipv4/tcp_output.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7d1efa7..78fc89c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2275,13 +2275,12 @@ void tcp_send_loss_probe(struct sock *sk)
 		tp->tlp_high_seq = tp->snd_nxt;
 
 rearm_timer:
-	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-				  inet_csk(sk)->icsk_rto,
-				  TCP_RTO_MAX);
-
-	if (likely(!err))
-		NET_INC_STATS_BH(sock_net(sk),
-				 LINUX_MIB_TCPLOSSPROBES);
+	if (likely(!err)) {
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSPROBES);
+		/* Reset s.t. tcp_rearm_rto will restart timer from now */
+		inet_csk(sk)->icsk_pending = 0;
+	}
+	tcp_rearm_rto(sk);
 }
 
 /* Push out any pending frames which were held back due to
-- 
2.5.0.276.gf5e568e

[PATCH net-next v2 2/2] tcp: TLP retransmits last if failed to send new packet

[Yuchung Cheng]

When TLP fails to send new packet because of receive window
limit, it should fall back to retransmit the last packet instead.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Nandita Dukkipati <nanditad@google.com>
---
v2: condition the fallback retransmit on receiver window limit

 net/ipv4/tcp_output.c | 38 ++++++++++++++++++++++----------------
 1 file changed, 22 insertions(+), 16 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 78fc89c..444ab5b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2149,7 +2149,7 @@ repair:
 		tcp_cwnd_validate(sk, is_cwnd_limited);
 		return false;
 	}
-	return (push_one == 2) || (!tp->packets_out && tcp_send_head(sk));
+	return !tp->packets_out && tcp_send_head(sk);
 }
 
 bool tcp_schedule_loss_probe(struct sock *sk)
@@ -2226,7 +2226,7 @@ static bool skb_still_in_host_queue(const struct sock *sk,
 	return false;
 }
 
-/* When probe timeout (PTO) fires, send a new segment if one exists, else
+/* When probe timeout (PTO) fires, try send a new segment if possible, else
  * retransmit the last segment.
  */
 void tcp_send_loss_probe(struct sock *sk)
@@ -2235,11 +2235,19 @@ void tcp_send_loss_probe(struct sock *sk)
 	struct sk_buff *skb;
 	int pcount;
 	int mss = tcp_current_mss(sk);
-	int err = -1;
 
-	if (tcp_send_head(sk)) {
-		err = tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC);
-		goto rearm_timer;
+	skb = tcp_send_head(sk);
+	if (skb) {
+		if (tcp_snd_wnd_test(tp, skb, mss)) {
+			pcount = tp->packets_out;
+			tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC);
+			if (tp->packets_out > pcount)
+				goto probe_sent;
+			goto rearm_timer;
+		}
+		skb = tcp_write_queue_prev(sk, skb);
+	} else {
+		skb = tcp_write_queue_tail(sk);
 	}
 
 	/* At most one outstanding TLP retransmission. */
@@ -2247,7 +2255,6 @@ void tcp_send_loss_probe(struct sock *sk)
 		goto rearm_timer;
 
 	/* Retransmit last segment. */
-	skb = tcp_write_queue_tail(sk);
 	if (WARN_ON(!skb))
 		goto rearm_timer;
 
@@ -2262,24 +2269,23 @@ void tcp_send_loss_probe(struct sock *sk)
 		if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss,
 					  GFP_ATOMIC)))
 			goto rearm_timer;
-		skb = tcp_write_queue_tail(sk);
+		skb = tcp_write_queue_next(sk, skb);
 	}
 
 	if (WARN_ON(!skb || !tcp_skb_pcount(skb)))
 		goto rearm_timer;
 
-	err = __tcp_retransmit_skb(sk, skb);
+	if (__tcp_retransmit_skb(sk, skb))
+		goto rearm_timer;
 
 	/* Record snd_nxt for loss detection. */
-	if (likely(!err))
-		tp->tlp_high_seq = tp->snd_nxt;
+	tp->tlp_high_seq = tp->snd_nxt;
 
+probe_sent:
+	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSPROBES);
+	/* Reset s.t. tcp_rearm_rto will restart timer from now */
+	inet_csk(sk)->icsk_pending = 0;
 rearm_timer:
-	if (likely(!err)) {
-		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSPROBES);
-		/* Reset s.t. tcp_rearm_rto will restart timer from now */
-		inet_csk(sk)->icsk_pending = 0;
-	}
 	tcp_rearm_rto(sk);
 }
 
-- 
2.5.0.276.gf5e568e

Re: [PATCH net-next v2 1/2] tcp: don't extend RTO on failed loss probe attempts

[Eric Dumazet]

On Wed, 2015-08-12 at 11:18 -0700, Yuchung Cheng wrote:
> If TLP was unable to send a probe, it extended the RTO to
> now + icsk_rto. But extending the RTO makes little sense
> if no TLP probe went out. With this commit, instead of
> extending the RTO we re-arm it relative to the transmit time
> of the write queue head.
> 
> Signed-off-by: Yuchung Cheng <ycheng@google.com>
> Signed-off-by: Neal Cardwell <ncardwell@google.com>
> Signed-off-by: Nandita Dukkipati <nanditad@google.com>
> ---

Acked-by: Eric Dumazet <edumazet@google.com>

Re: [PATCH net-next v2 0/2] minor tail loss probe improvements

[David Miller]

From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 12 Aug 2015 11:18:17 -0700

> This patch series enhance the tail loss probe (TLP) on some error
> conditions. When TLP fails to send a probe, it will no longer
> extend the RTO. When it fails to send a new packet because of
> receiver window limit, it'll try to retransmit the last packet.

Series applied, thanks.