tcp: do not aggressively quick ack after ECN events
authorEric Dumazet <edumazet@google.com>
Mon, 21 May 2018 22:08:57 +0000 (15:08 -0700)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Fri, 3 Aug 2018 05:50:45 +0000 (07:50 +0200)
commitfd31083cbe050d10b1cb4f681929154cffe18fb6
treeb3c5636aaf5a34206c590801dd22a39b48643b58
parent1c005489fa9876713d8f1f626947017dd45a9bfc
tcp: do not aggressively quick ack after ECN events

[ Upstream commit 522040ea5fdd1c33bbf75e1d7c7c0422b96a94ef ]

ECN signals currently forces TCP to enter quickack mode for
up to 16 (TCP_MAX_QUICKACKS) following incoming packets.

We believe this is not needed, and only sending one immediate ack
for the current packet should be enough.

This should reduce the extra load noticed in DCTCP environments,
after congestion events.

This is part 2 of our effort to reduce pure ACK packets.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
net/ipv4/tcp_input.c