summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
authorYuchung Cheng <ycheng@google.com>2018-01-17 12:11:01 -0800
committerDavid S. Miller <davem@davemloft.net>2018-01-19 15:39:30 -0500
commite42866031ff03c89a5bdd2056c76dd6cb41c3d35 (patch)
treef72181b7dfc5d58ee416a996028ea5c3698a206c /net/ipv4
parenteb36be0fd55e0a6f2cb3226acd711b2c7a2d7d09 (diff)
tcp: avoid min RTT bloat by skipping RTT from delayed-ACK in BBR
A persistent connection may send tiny amount of data (e.g. health-check) for a long period of time. BBR's windowed min RTT filter may only see RTT samples from delayed ACKs causing BBR to grossly over-estimate the path delay depending how much the ACK was delayed at the receiver. This patch skips RTT samples that are likely coming from delayed ACKs. Note that it is possible the sender never obtains a valid measure to set the min RTT. In this case BBR will continue to set cwnd to initial window which seems fine because the connection is thin stream. Signed-off-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Priyaranjan Jha <priyarjha@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/tcp_bbr.c3
-rw-r--r--net/ipv4/tcp_input.c1
2 files changed, 3 insertions, 1 deletions
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 8322f26e770e..785712be5b0d 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -766,7 +766,8 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs)
filter_expired = after(tcp_jiffies32,
bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ);
if (rs->rtt_us >= 0 &&
- (rs->rtt_us <= bbr->min_rtt_us || filter_expired)) {
+ (rs->rtt_us <= bbr->min_rtt_us ||
+ (filter_expired && !rs->is_ack_delayed))) {
bbr->min_rtt_us = rs->rtt_us;
bbr->min_rtt_stamp = tcp_jiffies32;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2c6797134553..cfa51cfd2d99 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3633,6 +3633,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */
lost = tp->lost - lost; /* freshly marked lost */
+ rs.is_ack_delayed = !!(flag & FLAG_ACK_MAYBE_DELAYED);
tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate);
tcp_cong_control(sk, ack, delivered, flag, sack_state.rate);
tcp_xmit_recovery(sk, rexmit);