From 2072c228c9a05c004a230620196da7607cdcc5b6 Mon Sep 17 00:00:00 2001 From: Gavin McCullagh Date: Sat, 29 Dec 2007 19:11:21 -0800 Subject: [PATCH] [TCP]: use non-delayed ACK for congestion control RTT MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit When a delayed ACK representing two packets arrives, there are two RTT samples available, one for each packet. The first (in order of seq number) will be artificially long due to the delay waiting for the second packet, the second will trigger the ACK and so will not itself be delayed. According to rfc1323, the SRTT used for RTO calculation should use the first rtt, so receivers echo the timestamp from the first packet in the delayed ack. For congestion control however, it seems measuring delayed ack delay is not desirable as it varies independently of congestion. The patch below causes seq_rtt and last_ackt to be updated with any available later packet rtts which should have less (and hopefully zero) delack delay. The rtt value then gets passed to ca_ops->pkts_acked(). Where TCP_CONG_RTT_STAMP was set, effort was made to supress RTTs from within a TSO chunk (!fully_acked), using only the final ACK (which includes any TSO delay) to generate RTTs. This patch removes these checks so RTTs are passed for each ACK to ca_ops->pkts_acked(). For non-delay based congestion control (cubic, h-tcp), rtt is sometimes used for rtt-scaling. In shortening the RTT, this may make them a little less aggressive. Delay-based schemes (eg vegas, veno, illinois) should get a cleaner, more accurate congestion signal, particularly for small cwnds. The congestion control module can potentially also filter out bad RTTs due to the delayed ack alarm by looking at the associated cnt which (where delayed acking is in use) should probably be 1 if the alarm went off or greater if the ACK was triggered by a packet. Signed-off-by: Gavin McCullagh Acked-by: Ilpo Järvinen Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 889c89362b..b39f0d86e4 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)) { @@ -2659,6 +2660,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, s32 *seq_rtt_p, u32 packets_acked; u8 sacked = scb->sacked; + /* Determine how many packets and what bytes were acked, tso and else */ if (after(scb->end_seq, tp->snd_una)) { if (tcp_skb_pcount(skb) == 1 || !after(tp->snd_una, scb->seq)) @@ -2686,15 +2688,16 @@ 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; + last_ackt = skb->tstamp; if (seq_rtt < 0) { - seq_rtt = now - scb->when; - if (fully_acked) - last_ackt = skb->tstamp; + seq_rtt = ca_seq_rtt; } if (!(sacked & TCPCB_SACKED_ACKED)) reord = min(cnt, reord); @@ -2709,10 +2712,10 @@ 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; + last_ackt = skb->tstamp; if (seq_rtt < 0) { - seq_rtt = now - scb->when; - if (fully_acked) - last_ackt = skb->tstamp; + seq_rtt = ca_seq_rtt; } reord = min(cnt, reord); } @@ -2772,8 +2775,8 @@ 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); -- 2.39.5