| Message ID | 20190829140244.195954-1-luke.w.hsiao@gmail.com |
|---|---|
| State | Accepted |
| Delegated to: | David Miller |
| Headers | show |
| Series | [net-next] tcp_bbr: clarify that bbr_bdp() rounds up in comments | expand |
From: Luke Hsiao <luke.w.hsiao@gmail.com> Date: Thu, 29 Aug 2019 10:02:44 -0400 > From: Luke Hsiao <lukehsiao@google.com> > > This explicitly clarifies that bbr_bdp() returns the rounded-up value of > the bandwidth-delay product and why in the comments. > > Signed-off-by: Luke Hsiao <lukehsiao@google.com> > Acked-by: Soheil Hassas Yeganeh <soheil@google.com> > Acked-by: Neal Cardwell <ncardwell@google.com> > Acked-by: Priyaranjan Jha <priyarjha@google.com> Applied.
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 56be7d27f208..95b59540eee1 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -346,7 +346,7 @@ static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) /* Calculate bdp based on min RTT and the estimated bottleneck bandwidth: * - * bdp = bw * min_rtt * gain + * bdp = ceil(bw * min_rtt * gain) * * The key factor, gain, controls the amount of queue. While a small gain * builds a smaller queue, it becomes more vulnerable to noise in RTT @@ -370,7 +370,9 @@ static u32 bbr_bdp(struct sock *sk, u32 bw, int gain) w = (u64)bw * bbr->min_rtt_us; - /* Apply a gain to the given value, then remove the BW_SCALE shift. */ + /* Apply a gain to the given value, remove the BW_SCALE shift, and + * round the value up to avoid a negative feedback loop. + */ bdp = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT; return bdp;