From a337531b942bd8a03e7052444d7e36972aac2d92 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Thu, 27 Sep 2018 11:21:19 -0700 Subject: tcp: up initial rmem to 128KB and SYN rwin to around 64KB Previously TCP initial receive buffer is ~87KB by default and the initial receive window is ~29KB (20 MSS). This patch changes the two numbers to 128KB and ~64KB (rounding down to the multiples of MSS) respectively. The patch also simplifies the calculations s.t. the two numbers are directly controlled by sysctl tcp_rmem[1]: 1) Initial receiver buffer budget (sk_rcvbuf): while this should be configured via sysctl tcp_rmem[1], previously tcp_fixup_rcvbuf() always override and set a larger size when a new connection establishes. 2) Initial receive window in SYN: previously it is set to 20 packets if MSS <= 1460. The number 20 was based on the initial congestion window of 10: the receiver needs twice amount to avoid being limited by the receive window upon out-of-order delivery in the first window burst. But since this only applies if the receiving MSS <= 1460, connection using large MTU (e.g. to utilize receiver zero-copy) may be limited by the receive window. With this patch TCP memory configuration is more straight-forward and more properly sized to modern high-speed networks by default. Several popular stacks have been announcing 64KB rwin in SYNs as well. Signed-off-by: Yuchung Cheng Signed-off-by: Wei Wang Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Reviewed-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 25 ++++--------------------- 1 file changed, 4 insertions(+), 21 deletions(-) (limited to 'net/ipv4/tcp_output.c') diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fe7855b090e4..059b67af28b1 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -195,21 +195,6 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } - -u32 tcp_default_init_rwnd(u32 mss) -{ - /* Initial receive window should be twice of TCP_INIT_CWND to - * enable proper sending of new unsent data during fast recovery - * (RFC 3517, Section 4, NextSeg() rule (2)). Further place a - * limit when mss is larger than 1460. - */ - u32 init_rwnd = TCP_INIT_CWND * 2; - - if (mss > 1460) - init_rwnd = max((1460 * init_rwnd) / mss, 2U); - return init_rwnd; -} - /* Determine a window scaling and initial window to offer. * Based on the assumption that the given amount of space * will be offered. Store the results in the tp structure. @@ -244,7 +229,10 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, if (sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows) (*rcv_wnd) = min(space, MAX_TCP_WINDOW); else - (*rcv_wnd) = space; + (*rcv_wnd) = min_t(u32, space, U16_MAX); + + if (init_rcv_wnd) + *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); (*rcv_wscale) = 0; if (wscale_ok) { @@ -257,11 +245,6 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, (*rcv_wscale)++; } } - - if (!init_rcv_wnd) /* Use default unless specified otherwise */ - init_rcv_wnd = tcp_default_init_rwnd(mss); - *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); - /* Set the clamp no higher than max representable value */ (*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp); } -- cgit v1.2.3-55-g7522