summaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp_hybla.c
diff options
context:
space:
mode:
authorEric Dumazet <edumazet@google.com>2014-02-26 14:02:48 -0800
committerDavid S. Miller <davem@davemloft.net>2014-02-26 17:08:40 -0500
commit740b0f1841f6e39085b711d41db9ffb07198682b (patch)
tree7befd549fc20c51bff4c79790ad4520fcc0e324e /net/ipv4/tcp_hybla.c
parent363ec392352e55c61ce2799c3f15f89f9429bba7 (diff)
tcp: switch rtt estimations to usec resolution
Upcoming congestion controls for TCP require usec resolution for RTT estimations. Millisecond resolution is simply not enough these days. FQ/pacing in DC environments also require this change for finer control and removal of bimodal behavior due to the current hack in tcp_update_pacing_rate() for 'small rtt' TCP_CONG_RTT_STAMP is no longer needed. As Julian Anastasov pointed out, we need to keep user compatibility : tcp_metrics used to export RTT and RTTVAR in msec resolution, so we added RTT_US and RTTVAR_US. An iproute2 patch is needed to use the new attributes if provided by the kernel. In this example ss command displays a srtt of 32 usecs (10Gbit link) lpk51:~# ./ss -i dst lpk52 Netid State Recv-Q Send-Q Local Address:Port Peer Address:Port tcp ESTAB 0 1 10.246.11.51:42959 10.246.11.52:64614 cubic wscale:6,6 rto:201 rtt:0.032/0.001 ato:40 mss:1448 cwnd:10 send 3620.0Mbps pacing_rate 7240.0Mbps unacked:1 rcv_rtt:993 rcv_space:29559 Updated iproute2 ip command displays : lpk51:~# ./ip tcp_metrics | grep 10.246.11.52 10.246.11.52 age 561.914sec cwnd 10 rtt 274us rttvar 213us source 10.246.11.51 Old binary displays : lpk51:~# ip tcp_metrics | grep 10.246.11.52 10.246.11.52 age 561.914sec cwnd 10 rtt 250us rttvar 125us source 10.246.11.51 With help from Julian Anastasov, Stephen Hemminger and Yuchung Cheng Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Cc: Stephen Hemminger <stephen@networkplumber.org> Cc: Yuchung Cheng <ycheng@google.com> Cc: Larry Brakmo <brakmo@google.com> Cc: Julian Anastasov <ja@ssi.bg> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/tcp_hybla.c')
-rw-r--r--net/ipv4/tcp_hybla.c12
1 files changed, 7 insertions, 5 deletions
diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c
index 2a1a9e2a4e5..a15a799bf76 100644
--- a/net/ipv4/tcp_hybla.c
+++ b/net/ipv4/tcp_hybla.c
@@ -21,7 +21,7 @@ struct hybla {
u32 rho2; /* Rho * Rho, integer part */
u32 rho_3ls; /* Rho parameter, <<3 */
u32 rho2_7ls; /* Rho^2, <<7 */
- u32 minrtt; /* Minimum smoothed round trip time value seen */
+ u32 minrtt_us; /* Minimum smoothed round trip time value seen */
};
/* Hybla reference round trip time (default= 1/40 sec = 25 ms), in ms */
@@ -35,7 +35,9 @@ static inline void hybla_recalc_param (struct sock *sk)
{
struct hybla *ca = inet_csk_ca(sk);
- ca->rho_3ls = max_t(u32, tcp_sk(sk)->srtt / msecs_to_jiffies(rtt0), 8);
+ ca->rho_3ls = max_t(u32,
+ tcp_sk(sk)->srtt_us / (rtt0 * USEC_PER_MSEC),
+ 8U);
ca->rho = ca->rho_3ls >> 3;
ca->rho2_7ls = (ca->rho_3ls * ca->rho_3ls) << 1;
ca->rho2 = ca->rho2_7ls >> 7;
@@ -59,7 +61,7 @@ static void hybla_init(struct sock *sk)
hybla_recalc_param(sk);
/* set minimum rtt as this is the 1st ever seen */
- ca->minrtt = tp->srtt;
+ ca->minrtt_us = tp->srtt_us;
tp->snd_cwnd = ca->rho;
}
@@ -94,9 +96,9 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked,
int is_slowstart = 0;
/* Recalculate rho only if this srtt is the lowest */
- if (tp->srtt < ca->minrtt){
+ if (tp->srtt_us < ca->minrtt_us) {
hybla_recalc_param(sk);
- ca->minrtt = tp->srtt;
+ ca->minrtt_us = tp->srtt_us;
}
if (!tcp_is_cwnd_limited(sk, in_flight))