From a657db0350bb8f568897835b6189c84a89f13292 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Tue, 27 Jul 2021 10:42:58 -0400 Subject: tcp: more accurately check DSACKs to grow RACK reordering window Previously, a DSACK could expand the RACK reordering window when no reordering has been seen, and/or when the DSACK was due to an unnecessary TLP retransmit (rather than a spurious fast recovery due to reordering). This could result in unnecessarily growing the RACK reordering window and thus unnecessarily delaying RACK-based fast recovery episodes. To avoid these issues, this commit tightens the conditions under which a DSACK triggers the RACK reordering window to grow, so that a connection only expands its RACK reordering window if: (a) reordering has been seen in the connection (b) a DSACKed range does not match the most recent TLP retransmit Signed-off-by: Neal Cardwell Acked-by: Yuchung Cheng Acked-by: Priyaranjan Jha Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 9 ++++++++- net/ipv4/tcp_recovery.c | 3 ++- 2 files changed, 10 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 98408d520c32..3f7bd7ae7d7a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1001,7 +1001,14 @@ static u32 tcp_dsack_seen(struct tcp_sock *tp, u32 start_seq, return 0; tp->rx_opt.sack_ok |= TCP_DSACK_SEEN; - tp->rack.dsack_seen = 1; + /* We increase the RACK ordering window in rounds where we receive + * DSACKs that may have been due to reordering causing RACK to trigger + * a spurious fast recovery. Thus RACK ignores DSACKs that happen + * without having seen reordering, or that match TLP probes (TLP + * is timer-driven, not triggered by RACK). + */ + if (tp->reord_seen && !(state->flag & FLAG_DSACK_TLP)) + tp->rack.dsack_seen = 1; state->flag |= FLAG_DSACKING_ACK; /* A spurious retransmission is delivered */ diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 6f1b4ac7fe99..fd113f6226ef 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -172,7 +172,8 @@ void tcp_rack_reo_timeout(struct sock *sk) /* Updates the RACK's reo_wnd based on DSACK and no. of recoveries. * - * If DSACK is received, increment reo_wnd by min_rtt/4 (upper bounded + * If a DSACK is received that seems like it may have been due to reordering + * triggering fast recovery, increment reo_wnd by min_rtt/4 (upper bounded * by srtt), since there is possibility that spurious retransmission was * due to reordering delay longer than reo_wnd. * -- cgit v1.2.3