[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <20230906201046.463236-1-edumazet@google.com>
Date: Wed, 6 Sep 2023 20:10:42 +0000
From: Eric Dumazet <edumazet@...gle.com>
To: "David S . Miller" <davem@...emloft.net>, Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>
Cc: netdev@...r.kernel.org, eric.dumazet@...il.com,
Soheil Hassas Yeganeh <soheil@...gle.com>, Neal Cardwell <ncardwell@...gle.com>,
Yuchung Cheng <ycheng@...gle.com>, Eric Dumazet <edumazet@...gle.com>
Subject: [RFC net-next 0/4] tcp: backlog processing optims
First patches are mostly preparing the ground for the last one.
Last patch of the series implements sort of ACK reduction
only for the cases a TCP receiver is under high stress,
which happens for high throughput flows.
This gives us a ~20% increase of single TCP flow (100Gbit -> 120Gbit)
Eric Dumazet (4):
tcp: no longer release socket ownership in tcp_release_cb()
net: sock_release_ownership() cleanup
net: call prot->release_cb() when processing backlog
tcp: defer regular ACK while processing socket backlog
Documentation/networking/ip-sysctl.rst | 7 +++++++
include/linux/tcp.h | 14 ++++++++------
include/net/netns/ipv4.h | 1 +
include/net/sock.h | 9 ++++-----
net/core/sock.c | 6 +++---
net/ipv4/sysctl_net_ipv4.c | 9 +++++++++
net/ipv4/tcp_input.c | 8 ++++++++
net/ipv4/tcp_ipv4.c | 1 +
net/ipv4/tcp_output.c | 15 ++++-----------
9 files changed, 45 insertions(+), 25 deletions(-)
--
2.42.0.283.g2d96d420d3-goog
Powered by blists - more mailing lists