diff mbox series

[SRU,B/aws,F/aws,G/aws,1/1] tcp: select sane initial rcvq_space.space for big MSS

Message ID 20210105074442.108187-2-andrea.righi@canonical.com
State New
Headers show
Series aws: fix network performance regression due to initial TCP buffer size change | expand

Commit Message

Andrea Righi Jan. 5, 2021, 7:44 a.m. UTC 
From: Eric Dumazet <edumazet@google.com>

BugLink: https://bugs.launchpad.net/bugs/1910200

Before commit a337531b942b ("tcp: up initial rmem to 128KB and SYN rwin to around 64KB")
small tcp_rmem[1] values were overridden by tcp_fixup_rcvbuf() to accommodate various MSS.

This is no longer the case, and Hazem Mohamed Abuelfotoh reported
that DRS would not work for MTU 9000 endpoints receiving regular (1500 bytes) frames.

Root cause is that tcp_init_buffer_space() uses tp->rcv_wnd for upper limit
of rcvq_space.space computation, while it can select later a smaller
value for tp->rcv_ssthresh and tp->window_clamp.

ss -temoi on receiver would show :

skmem:(r0,rb131072,t0,tb46080,f0,w0,o0,bl0,d0) rcv_space:62496 rcv_ssthresh:56596

This means that TCP can not increase its window in tcp_grow_window(),
and that DRS can never kick.

Fix this by making sure that rcvq_space.space is not bigger than number of bytes
that can be held in TCP receive queue.

People unable/unwilling to change their kernel can work around this issue by
selecting a bigger tcp_rmem[1] value as in :

echo "4096 196608 6291456" >/proc/sys/net/ipv4/tcp_rmem

Based on an initial report and patch from Hazem Mohamed Abuelfotoh
 https://lore.kernel.org/netdev/20201204180622.14285-1-abuehaze@amazon.com/

Fixes: a337531b942b ("tcp: up initial rmem to 128KB and SYN rwin to around 64KB")
Fixes: 041a14d26715 ("tcp: start receiver buffer autotuning sooner")
Reported-by: Hazem Mohamed Abuelfotoh <abuehaze@amazon.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 72d05c00d7ecda85df29abd046da7e41cc071c17)
Signed-off-by: Andrea Righi <andrea.righi@canonical.com>
---
 net/ipv4/tcp_input.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6c7e98216946..e65b921b2e26 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -447,7 +447,6 @@  static void tcp_init_buffer_space(struct sock *sk)
 	if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK))
 		tcp_sndbuf_expand(sk);
 
-	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;
@@ -471,6 +470,8 @@  static void tcp_init_buffer_space(struct sock *sk)
 
 	tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp);
 	tp->snd_cwnd_stamp = tcp_jiffies32;
+	tp->rcvq_space.space = min3(tp->rcv_ssthresh, tp->rcv_wnd,
+				    (u32)TCP_INIT_CWND * tp->advmss);
 }
 
 /* 4. Recalculate window clamp after socket hit its memory bounds. */