From 645f4c6f2ebd040688cc2a5f626ffc909e66ccf2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 25 Apr 2017 10:15:41 -0700 Subject: 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 Acked-by: Soheil Hassas Yeganeh Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux/tcp.h') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 99a22f44c32e..b6d5adcee8fc 100644 --- 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. */ -- cgit v1.2.3