tcp: remove 1ms offset in srtt computation
TCP pacing depends on an accurate srtt estimation. Current srtt estimation is using jiffie resolution, and has an artificial offset of at least 1 ms, which can produce slowdowns when FQ/pacing is used, especially in DC world, where typical rtt is below 1 ms. We are planning a switch to usec resolution for linux-3.15, but in the meantime, this patch removes the 1 ms offset. All we need is to have tp->srtt minimal value of 1 to differentiate the case of srtt being initialized or not, not 8. The problematic behavior was observed on a 40Gbit testbed, where 32 concurrent netperf were reaching 12Gbps of aggregate speed, instead of line speed. This patch also has the effect of reporting more accurate srtt and send rates to iproute2 ss command as in : $ ss -i dst cca2 Netid State Recv-Q Send-Q Local Address:Port Peer Address:Port tcp ESTAB 0 0 10.244.129.1:56984 10.244.129.2:12865 cubic wscale:6,6 rto:200 rtt:0.25/0.25 ato:40 mss:1448 cwnd:10 send 463.4Mbps rcv_rtt:1 rcv_space:29200 tcp ESTAB 0 390960 10.244.129.1:60247 10.244.129.2:50204 cubic wscale:6,6 rto:200 rtt:0.875/0.75 mss:1448 cwnd:73 ssthresh:51 send 966.4Mbps unacked:73 retrans:0/121 rcv_space:29200 Reported-by: Vytautas Valancius <valas@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Neal Cardwell <ncardwell@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>hifive-unleashed-5.1
parent
dbe173079a
commit
4a5ab4e224
|
@ -671,6 +671,7 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
|
||||||
{
|
{
|
||||||
struct tcp_sock *tp = tcp_sk(sk);
|
struct tcp_sock *tp = tcp_sk(sk);
|
||||||
long m = mrtt; /* RTT */
|
long m = mrtt; /* RTT */
|
||||||
|
u32 srtt = tp->srtt;
|
||||||
|
|
||||||
/* The following amusing code comes from Jacobson's
|
/* The following amusing code comes from Jacobson's
|
||||||
* article in SIGCOMM '88. Note that rtt and mdev
|
* article in SIGCOMM '88. Note that rtt and mdev
|
||||||
|
@ -688,11 +689,9 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
|
||||||
* does not matter how to _calculate_ it. Seems, it was trap
|
* does not matter how to _calculate_ it. Seems, it was trap
|
||||||
* that VJ failed to avoid. 8)
|
* that VJ failed to avoid. 8)
|
||||||
*/
|
*/
|
||||||
if (m == 0)
|
if (srtt != 0) {
|
||||||
m = 1;
|
m -= (srtt >> 3); /* m is now error in rtt est */
|
||||||
if (tp->srtt != 0) {
|
srtt += m; /* rtt = 7/8 rtt + 1/8 new */
|
||||||
m -= (tp->srtt >> 3); /* m is now error in rtt est */
|
|
||||||
tp->srtt += m; /* rtt = 7/8 rtt + 1/8 new */
|
|
||||||
if (m < 0) {
|
if (m < 0) {
|
||||||
m = -m; /* m is now abs(error) */
|
m = -m; /* m is now abs(error) */
|
||||||
m -= (tp->mdev >> 2); /* similar update on mdev */
|
m -= (tp->mdev >> 2); /* similar update on mdev */
|
||||||
|
@ -723,11 +722,12 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
|
||||||
}
|
}
|
||||||
} else {
|
} else {
|
||||||
/* no previous measure. */
|
/* no previous measure. */
|
||||||
tp->srtt = m << 3; /* take the measured time to be rtt */
|
srtt = m << 3; /* take the measured time to be rtt */
|
||||||
tp->mdev = m << 1; /* make sure rto = 3*rtt */
|
tp->mdev = m << 1; /* make sure rto = 3*rtt */
|
||||||
tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
|
tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
|
||||||
tp->rtt_seq = tp->snd_nxt;
|
tp->rtt_seq = tp->snd_nxt;
|
||||||
}
|
}
|
||||||
|
tp->srtt = max(1U, srtt);
|
||||||
}
|
}
|
||||||
|
|
||||||
/* Set the sk_pacing_rate to allow proper sizing of TSO packets.
|
/* Set the sk_pacing_rate to allow proper sizing of TSO packets.
|
||||||
|
@ -746,8 +746,10 @@ static void tcp_update_pacing_rate(struct sock *sk)
|
||||||
|
|
||||||
rate *= max(tp->snd_cwnd, tp->packets_out);
|
rate *= max(tp->snd_cwnd, tp->packets_out);
|
||||||
|
|
||||||
/* Correction for small srtt : minimum srtt being 8 (1 jiffy << 3),
|
/* Correction for small srtt and scheduling constraints.
|
||||||
* be conservative and assume srtt = 1 (125 us instead of 1.25 ms)
|
* For small rtt, consider noise is too high, and use
|
||||||
|
* the minimal value (srtt = 1 -> 125 us for HZ=1000)
|
||||||
|
*
|
||||||
* We probably need usec resolution in the future.
|
* We probably need usec resolution in the future.
|
||||||
* Note: This also takes care of possible srtt=0 case,
|
* Note: This also takes care of possible srtt=0 case,
|
||||||
* when tcp_rtt_estimator() was not yet called.
|
* when tcp_rtt_estimator() was not yet called.
|
||||||
|
|
|
@ -1977,7 +1977,7 @@ bool tcp_schedule_loss_probe(struct sock *sk)
|
||||||
/* Schedule a loss probe in 2*RTT for SACK capable connections
|
/* Schedule a loss probe in 2*RTT for SACK capable connections
|
||||||
* in Open state, that are either limited by cwnd or application.
|
* in Open state, that are either limited by cwnd or application.
|
||||||
*/
|
*/
|
||||||
if (sysctl_tcp_early_retrans < 3 || !rtt || !tp->packets_out ||
|
if (sysctl_tcp_early_retrans < 3 || !tp->srtt || !tp->packets_out ||
|
||||||
!tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
|
!tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
|
||||||
return false;
|
return false;
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue