| Message ID | 20180727211912.241232-1-ncardwell@google.com |
|---|---|
| State | Accepted, archived |
| Delegated to: | David Miller |
| Headers | show |
| Series | [net] tcp_bbr: fix bw probing to raise in-flight data for very small BDPs | expand |
From: Neal Cardwell <ncardwell@google.com> Date: Fri, 27 Jul 2018 17:19:12 -0400 > For some very small BDPs (with just a few packets) there was a > quantization effect where the target number of packets in flight > during the super-unity-gain (1.25x) phase of gain cycling was > implicitly truncated to a number of packets no larger than the normal > unity-gain (1.0x) phase of gain cycling. This meant that in multi-flow > scenarios some flows could get stuck with a lower bandwidth, because > they did not push enough packets inflight to discover that there was > more bandwidth available. This was really only an issue in multi-flow > LAN scenarios, where RTTs and BDPs are low enough for this to be an > issue. > > This fix ensures that gain cycling can raise inflight for small BDPs > by ensuring that in PROBE_BW mode target inflight values with a > super-unity gain are always greater than inflight values with a gain > <= 1. Importantly, this applies whether the inflight value is > calculated for use as a cwnd value, or as a target inflight value for > the end of the super-unity phase in bbr_is_next_cycle_phase() (both > need to be bigger to ensure we can probe with more packets in flight > reliably). > > This is a candidate fix for stable releases. > > Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control") > Signed-off-by: Neal Cardwell <ncardwell@google.com> > Acked-by: Yuchung Cheng <ycheng@google.com> > Acked-by: Soheil Hassas Yeganeh <soheil@google.com> > Acked-by: Priyaranjan Jha <priyarjha@google.com> > Reviewed-by: Eric Dumazet <edumazet@google.com> Applied and queued up for -stable, thank you.
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 3b5f45b9e81eb..13d34427ca3dd 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -358,6 +358,10 @@ static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain) /* Reduce delayed ACKs by rounding up cwnd to the next even number. */ cwnd = (cwnd + 1) & ~1U; + /* Ensure gain cycling gets inflight above BDP even for small BDPs. */ + if (bbr->mode == BBR_PROBE_BW && gain > BBR_UNIT) + cwnd += 2; + return cwnd; }
For some very small BDPs (with just a few packets) there was a quantization effect where the target number of packets in flight during the super-unity-gain (1.25x) phase of gain cycling was implicitly truncated to a number of packets no larger than the normal unity-gain (1.0x) phase of gain cycling. This meant that in multi-flow scenarios some flows could get stuck with a lower bandwidth, because they did not push enough packets inflight to discover that there was more bandwidth available. This was really only an issue in multi-flow LAN scenarios, where RTTs and BDPs are low enough for this to be an issue. This fix ensures that gain cycling can raise inflight for small BDPs by ensuring that in PROBE_BW mode target inflight values with a super-unity gain are always greater than inflight values with a gain <= 1. Importantly, this applies whether the inflight value is calculated for use as a cwnd value, or as a target inflight value for the end of the super-unity phase in bbr_is_next_cycle_phase() (both need to be bigger to ensure we can probe with more packets in flight reliably). This is a candidate fix for stable releases. Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control") Signed-off-by: Neal Cardwell <ncardwell@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Priyaranjan Jha <priyarjha@google.com> Reviewed-by: Eric Dumazet <edumazet@google.com> --- net/ipv4/tcp_bbr.c | 4 ++++ 1 file changed, 4 insertions(+)