tcp: switch rcv_rtt_est and rcvq_space to high resolution timestamps

Some devices or distributions use HZ=100 or HZ=250

TCP receive buffer autotuning has poor behavior caused by this choice.
Since autotuning happens after 4 ms or 10 ms, short distance flows
get their receive buffer tuned to a very high value, but after an initial
period where it was frozen to (too small) initial value.

With tp->tcp_mstamp introduction, we can switch to high resolution
timestamps almost for free (at the expense of 8 additional bytes per
TCP structure)

Note that some TCP stacks use usec TCP timestamps where this
patch makes even more sense : Many TCP flows have < 500 usec RTT.
Hopefully this finer TS option can be standardized soon.

Tested:
 HZ=100 kernel
 ./netperf -H lpaa24 -t TCP_RR -l 1000 -- -r 10000,10000 &

 Peer without patch :
 lpaa24:~# ss -tmi dst lpaa23
 ...
 skmem:(r0,rb8388608,...)
 rcv_rtt:10 rcv_space:3210000 minrtt:0.017

 Peer with the patch :
 lpaa23:~# ss -tmi dst lpaa24
 ...
 skmem:(r0,rb428800,...)
 rcv_rtt:0.069 rcv_space:30000 minrtt:0.017

We can see saner RCVBUF, and more precise rcv_rtt information.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 99a22f44c32e1587a6bf4835b65c7a4314807aa8..b6d5adcee8fcb611de202993623cc80274d262e4 100644 (file)
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -333,16 +333,16 @@ struct tcp_sock {
 
 /* Receiver side RTT estimation */
        struct {
-               u32     rtt;
-               u32     seq;
-               u32     time;
+               u32             rtt_us;
+               u32             seq;
+               struct skb_mstamp time;
        } rcv_rtt_est;
 
 /* Receiver queue space */
        struct {
-               int     space;
-               u32     seq;
-               u32     time;
+               int             space;
+               u32             seq;
+               struct skb_mstamp time;
        } rcvq_space;
 
 /* TCP-specific MTU probe information. */

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index efc976ae66ae5b82d496323634c3030fb71c6c92..059dad7deefe883bd3a26c93f27637dc22ccefda 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2853,7 +2853,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
        info->tcpi_snd_ssthresh = tp->snd_ssthresh;
        info->tcpi_advmss = tp->advmss;
 
-       info->tcpi_rcv_rtt = jiffies_to_usecs(tp->rcv_rtt_est.rtt)>>3;
+       info->tcpi_rcv_rtt = tp->rcv_rtt_est.rtt_us >> 3;
        info->tcpi_rcv_space = tp->rcvq_space.space;
 
        info->tcpi_total_retrans = tp->total_retrans;

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index f475f0b53bfe4cb67c19b7f30d9d68bd703ff23b..9739962bfb3fd2d39cb13f643def223f4f17fcb6 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -442,7 +442,8 @@ void tcp_init_buffer_space(struct sock *sk)
                tcp_sndbuf_expand(sk);
 
        tp->rcvq_space.space = tp->rcv_wnd;
-       tp->rcvq_space.time = tcp_time_stamp;
+       skb_mstamp_get(&tp->tcp_mstamp);
+       tp->rcvq_space.time = tp->tcp_mstamp;
        tp->rcvq_space.seq = tp->copied_seq;
 
        maxwin = tcp_full_space(sk);
@@ -518,7 +519,7 @@ EXPORT_SYMBOL(tcp_initialize_rcv_mss);
  */
 static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
 {
-       u32 new_sample = tp->rcv_rtt_est.rtt;
+       u32 new_sample = tp->rcv_rtt_est.rtt_us;
        long m = sample;
 
        if (m == 0)
@@ -548,21 +549,23 @@ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
                new_sample = m << 3;
        }
 
-       if (tp->rcv_rtt_est.rtt != new_sample)
-               tp->rcv_rtt_est.rtt = new_sample;
+       tp->rcv_rtt_est.rtt_us = new_sample;
 }
 
 static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp)
 {
-       if (tp->rcv_rtt_est.time == 0)
+       u32 delta_us;
+
+       if (tp->rcv_rtt_est.time.v64 == 0)
                goto new_measure;
        if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq))
                return;
-       tcp_rcv_rtt_update(tp, tcp_time_stamp - tp->rcv_rtt_est.time, 1);
+       delta_us = skb_mstamp_us_delta(&tp->tcp_mstamp, &tp->rcv_rtt_est.time);
+       tcp_rcv_rtt_update(tp, delta_us, 1);
 
 new_measure:
        tp->rcv_rtt_est.seq = tp->rcv_nxt + tp->rcv_wnd;
-       tp->rcv_rtt_est.time = tcp_time_stamp;
+       tp->rcv_rtt_est.time = tp->tcp_mstamp;
 }
 
 static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
@@ -572,7 +575,10 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
        if (tp->rx_opt.rcv_tsecr &&
            (TCP_SKB_CB(skb)->end_seq -
             TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss))
-               tcp_rcv_rtt_update(tp, tcp_time_stamp - tp->rx_opt.rcv_tsecr, 0);
+               tcp_rcv_rtt_update(tp,
+                                  jiffies_to_usecs(tcp_time_stamp -
+                                                   tp->rx_opt.rcv_tsecr),
+                                  0);
 }
 
 /*
@@ -585,8 +591,8 @@ void tcp_rcv_space_adjust(struct sock *sk)
        int time;
        int copied;
 
-       time = tcp_time_stamp - tp->rcvq_space.time;
-       if (time < (tp->rcv_rtt_est.rtt >> 3) || tp->rcv_rtt_est.rtt == 0)
+       time = skb_mstamp_us_delta(&tp->tcp_mstamp, &tp->rcvq_space.time);
+       if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0)
                return;
 
        /* Number of bytes copied to user in last RTT */
@@ -642,7 +648,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 
 new_measure:
        tp->rcvq_space.seq = tp->copied_seq;
-       tp->rcvq_space.time = tcp_time_stamp;
+       tp->rcvq_space.time = tp->tcp_mstamp;
 }
 
 /* There is something which you must keep in mind when you analyze the