netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Yuchung Cheng <ycheng@google.com>
To: davem@davemloft.net, edumazet@google.com
Cc: netdev@vger.kernel.org, ncardwell@google.com, soheil@google.com,
	Yuchung Cheng <ycheng@google.com>
Subject: [PATCH net-next 0/8] undo congestion window on spurious SYN or SYNACK timeout
Date: Mon, 29 Apr 2019 15:46:12 -0700	[thread overview]
Message-ID: <20190429224620.151064-1-ycheng@google.com> (raw)

Linux TCP currently uses the initial congestion window of 1 packet
if multiple SYN or SYNACK timeouts per RFC6298. However such
timeouts are often spurious on wireless or cellular networks that
experience high delay variances (e.g. ramping up dormant radios or
local link retransmission). Another case is when the underlying
path is longer than the default SYN timeout (e.g. 1 second). In
these cases starting the transfer with a minimal congestion window
is detrimental to the performance for short flows.

One naive approach is to simply ignore SYN or SYNACK timeouts and
always use a larger or default initial window. This approach however
risks pouring gas to the fire when the network is already highly
congested. This is particularly true in data center where application
could start thousands to millions of connections over a single or
multiple hosts resulting in high SYN drops (e.g. incast).

This patch-set detects spurious SYN and SYNACK timeouts upon
completing the handshake via the widely-supported TCP timestamp
options. Upon such events the sender reverts to the default
initial window to start the data transfer so it gets best of both
worlds. This patch-set supports this feature for both active and
passive as well as Fast Open or regular connections.


Yuchung Cheng (8):
  tcp: avoid unconditional congestion window undo on SYN retransmit
  tcp: undo initial congestion window on false SYN timeout
  tcp: better SYNACK sent timestamp
  tcp: undo init congestion window on false SYNACK timeout
  tcp: lower congestion window on Fast Open SYNACK timeout
  tcp: undo cwnd on Fast Open spurious SYNACK retransmit
  tcp: refactor to consolidate TFO passive open code
  tcp: refactor setting the initial congestion window

 net/ipv4/tcp.c           | 12 -----
 net/ipv4/tcp_input.c     | 99 +++++++++++++++++++++++++++++-----------
 net/ipv4/tcp_metrics.c   | 10 ----
 net/ipv4/tcp_minisocks.c |  5 ++
 net/ipv4/tcp_output.c    |  4 ++
 net/ipv4/tcp_timer.c     |  3 ++
 6 files changed, 84 insertions(+), 49 deletions(-)

-- 
2.21.0.593.g511ec345e18-goog


             reply	other threads:[~2019-04-29 22:46 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-04-29 22:46 Yuchung Cheng [this message]
2019-04-29 22:46 ` [PATCH net-next 1/8] tcp: avoid unconditional congestion window undo on SYN retransmit Yuchung Cheng
2019-04-29 22:46 ` [PATCH net-next 2/8] tcp: undo initial congestion window on false SYN timeout Yuchung Cheng
2019-04-29 22:46 ` [PATCH net-next 3/8] tcp: better SYNACK sent timestamp Yuchung Cheng
2019-04-29 22:46 ` [PATCH net-next 4/8] tcp: undo init congestion window on false SYNACK timeout Yuchung Cheng
2019-06-19 15:54   ` Eric Dumazet
2019-04-29 22:46 ` [PATCH net-next 5/8] tcp: lower congestion window on Fast Open " Yuchung Cheng
2019-04-29 22:46 ` [PATCH net-next 6/8] tcp: undo cwnd on Fast Open spurious SYNACK retransmit Yuchung Cheng
2019-04-29 22:46 ` [PATCH net-next 7/8] tcp: refactor to consolidate TFO passive open code Yuchung Cheng
2019-04-29 22:46 ` [PATCH net-next 8/8] tcp: refactor setting the initial congestion window Yuchung Cheng
2019-05-01 15:55 ` [PATCH net-next 0/8] undo congestion window on spurious SYN or SYNACK timeout David Miller

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190429224620.151064-1-ycheng@google.com \
    --to=ycheng@google.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=ncardwell@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=soheil@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).