tcp: use windowed min filter library for TCP min_rtt estimation (64033892) · Commits · 戴 / test

include/linux/tcp.h

+2 −3

Original line number	Diff line number	Diff line
		@@ -19,6 +19,7 @@


		#include <linux/skbuff.h>
		#include <linux/win_minmax.h>
		#include <net/sock.h>
		#include <net/inet_connection_sock.h>
		#include <net/inet_timewait_sock.h>
		@@ -234,9 +235,7 @@ struct tcp_sock {
		u32 mdev_max_us; /* maximal mdev for the last rtt period */
		u32 rttvar_us; /* smoothed mdev_max */
		u32 rtt_seq; /* sequence number to update rttvar */
		struct rtt_meas {
		u32 rtt, ts; /* RTT in usec and sampling time in jiffies. */
		} rtt_min[3];
		struct minmax rtt_min;

		u32 packets_out; /* Packets which are "in flight" */
		u32 retrans_out; /* Retransmitted packets out */

include/net/tcp.h

+1 −1

Original line number	Diff line number	Diff line
		@@ -671,7 +671,7 @@ static inline bool tcp_ca_dst_locked(const struct dst_entry *dst)
		/* Minimum RTT in usec. ~0 means not available. */
		static inline u32 tcp_min_rtt(const struct tcp_sock *tp)
		{
		return tp->rtt_min[0].rtt;
		return minmax_get(&tp->rtt_min);
		}

		/* Compute the actual receive window we are currently advertising.

net/ipv4/tcp.c

+1 −1

Original line number	Diff line number	Diff line
		@@ -387,7 +387,7 @@ void tcp_init_sock(struct sock *sk)

		icsk->icsk_rto = TCP_TIMEOUT_INIT;
		tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
		tp->rtt_min[0].rtt = ~0U;
		minmax_reset(&tp->rtt_min, tcp_time_stamp, ~0U);

		/* So many TCP implementations out there (incorrectly) count the
		* initial SYN frame in their delayed-ACK and congestion control

net/ipv4/tcp_input.c

+5 −59

Original line number	Diff line number	Diff line
		@@ -2879,67 +2879,13 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked,
		*rexmit = REXMIT_LOST;
		}

		/* Kathleen Nichols' algorithm for tracking the minimum value of
		* a data stream over some fixed time interval. (E.g., the minimum
		* RTT over the past five minutes.) It uses constant space and constant
		* time per update yet almost always delivers the same minimum as an
		* implementation that has to keep all the data in the window.
		*
		* The algorithm keeps track of the best, 2nd best & 3rd best min
		* values, maintaining an invariant that the measurement time of the
		* n'th best >= n-1'th best. It also makes sure that the three values
		* are widely separated in the time window since that bounds the worse
		* case error when that data is monotonically increasing over the window.
		*
		* Upon getting a new min, we can forget everything earlier because it
		* has no value - the new min is <= everything else in the window by
		* definition and it's the most recent. So we restart fresh on every new min
		* and overwrites 2nd & 3rd choices. The same property holds for 2nd & 3rd
		* best.
		*/
		static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us)
		{
		const u32 now = tcp_time_stamp, wlen = sysctl_tcp_min_rtt_wlen * HZ;
		struct rtt_meas *m = tcp_sk(sk)->rtt_min;
		struct rtt_meas rttm = {
		.rtt = likely(rtt_us) ? rtt_us : jiffies_to_usecs(1),
		.ts = now,
		};
		u32 elapsed;

		/* Check if the new measurement updates the 1st, 2nd, or 3rd choices */
		if (unlikely(rttm.rtt <= m[0].rtt))
		m[0] = m[1] = m[2] = rttm;
		else if (rttm.rtt <= m[1].rtt)
		m[1] = m[2] = rttm;
		else if (rttm.rtt <= m[2].rtt)
		m[2] = rttm;

		elapsed = now - m[0].ts;
		if (unlikely(elapsed > wlen)) {
		/* Passed entire window without a new min so make 2nd choice
		* the new min & 3rd choice the new 2nd. So forth and so on.
		*/
		m[0] = m[1];
		m[1] = m[2];
		m[2] = rttm;
		if (now - m[0].ts > wlen) {
		m[0] = m[1];
		m[1] = rttm;
		if (now - m[0].ts > wlen)
		m[0] = rttm;
		}
		} else if (m[1].ts == m[0].ts && elapsed > wlen / 4) {
		/* Passed a quarter of the window without a new min so
		* take 2nd choice from the 2nd quarter of the window.
		*/
		m[2] = m[1] = rttm;
		} else if (m[2].ts == m[1].ts && elapsed > wlen / 2) {
		/* Passed half the window without a new min so take the 3rd
		* choice from the last half of the window.
		*/
		m[2] = rttm;
		}
		struct tcp_sock *tp = tcp_sk(sk);
		u32 wlen = sysctl_tcp_min_rtt_wlen * HZ;

		minmax_running_min(&tp->rtt_min, wlen, tcp_time_stamp,
		rtt_us ? : jiffies_to_usecs(1));
		}

		static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,

net/ipv4/tcp_minisocks.c

+1 −1

Original line number	Diff line number	Diff line
		@@ -464,7 +464,7 @@ struct sock tcp_create_openreq_child(const struct sock sk,

		newtp->srtt_us = 0;
		newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
		newtp->rtt_min[0].rtt = ~0U;
		minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U);
		newicsk->icsk_rto = TCP_TIMEOUT_INIT;

		newtp->packets_out = 0;

Admin message