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.
This patch also lowers the initial bytes expected to receive in
the receiver buffer autotuning algorithm - otherwise the receiver
may take two to three rounds to increase the buffer to the
appropriate level (2x sender congestion 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 <ych...@google.com>
Signed-off-by: Wei Wang <wei...@google.com>
Signed-off-by: Neal Cardwell <ncardw...@google.com>
Signed-off-by: Eric Dumazet <eduma...@google.com>
Reviewed-by: Soheil Hassas Yeganeh <soh...@google.com>
---
net/ipv4/tcp.c | 4 ++--
net/ipv4/tcp_input.c | 30 +++++-------------------------
net/ipv4/tcp_output.c | 25 ++++---------------------
3 files changed, 11 insertions(+), 48 deletions(-)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 69c236943f56..dcf51fbf5ec7 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3896,8 +3896,8 @@ void __init tcp_init(void)
init_net.ipv4.sysctl_tcp_wmem[2] = max(64*1024, max_wshare);
init_net.ipv4.sysctl_tcp_rmem[0] = SK_MEM_QUANTUM;
- init_net.ipv4.sysctl_tcp_rmem[1] = 87380;
- init_net.ipv4.sysctl_tcp_rmem[2] = max(87380, max_rshare);
+ init_net.ipv4.sysctl_tcp_rmem[1] = 131072;
+ init_net.ipv4.sysctl_tcp_rmem[2] = max(131072, max_rshare);
pr_info("Hash tables configured (established %u bind %u)\n",
tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d703a0b3b6a2..4f714a031618 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -426,27 +426,9 @@ static void tcp_grow_window(struct sock *sk, const struct
sk_buff *skb)
}
}
-/* 3. Tuning rcvbuf, when connection enters established state. */
-static void tcp_fixup_rcvbuf(struct sock *sk)
-{
- u32 mss = tcp_sk(sk)->advmss;
- int rcvmem;
-
- rcvmem = 2 * SKB_TRUESIZE(mss + MAX_TCP_HEADER) *
- tcp_default_init_rwnd(mss);
-
- /* Dynamic Right Sizing (DRS) has 2 to 3 RTT latency
- * Allow enough cushion so that sender is not limited by our window
- */
- if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)
- rcvmem <<= 2;
-
- if (sk->sk_rcvbuf < rcvmem)
- sk->sk_rcvbuf = min(rcvmem,
sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
-}
-
-/* 4. Try to fixup all. It is made immediately after connection enters
- * established state.
+/* 3. Try to fixup all. It is made immediately after connection enters
+ * established state. Budget the space to the expected initial window
+ * of burst to auto-tune the receive buffer right after the first round.
*/
void tcp_init_buffer_space(struct sock *sk)
{
@@ -454,12 +436,10 @@ void tcp_init_buffer_space(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
int maxwin;
- if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK))
- tcp_fixup_rcvbuf(sk);
if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK))
tcp_sndbuf_expand(sk);
- tp->rcvq_space.space = tp->rcv_wnd;
+ tp->rcvq_space.space = min_t(u32, tp->rcv_wnd, TCP_INIT_CWND *
tp->advmss);
tcp_mstamp_refresh(tp);
tp->rcvq_space.time = tp->tcp_mstamp;
tp->rcvq_space.seq = tp->copied_seq;
@@ -485,7 +465,7 @@ void tcp_init_buffer_space(struct sock *sk)
tp->snd_cwnd_stamp = tcp_jiffies32;
}
-/* 5. Recalculate window clamp after socket hit its memory bounds. */
+/* 4. Recalculate window clamp after socket hit its memory bounds. */
static void tcp_clamp_window(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
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);
}
--
2.19.0.605.g01d371f741-goog
