From: Per Hurtig <per.hurtig@kau.se>
To: davem@davemloft.net, edumazet@google.com, ncardwell@google.com,
nanditad@google.com, tom@herbertland.com, ycheng@google.com,
viro@zeniv.linux.org.uk, fw@strlen.de, mleitner@redhat.com,
daniel@iogearbox.net, willemb@google.com,
ilpo.jarvinen@helsinki.fi, pasi.sarolahti@iki.fi,
stephen@networkplumber.org, netdev@vger.kernel.org
Cc: anna.brunstrom@kau.se, apetlund@simula.no, michawe@ifi.uio.no,
mohammad.rajiullah@kau.se, Per Hurtig <per.hurtig@kau.se>
Subject: [RFC PATCHv2 net-next 0/2] tcp: timer restart for tail loss
Date: Tue, 8 Dec 2015 10:19:41 +0100 [thread overview]
Message-ID: <cover.1449561786.git.per.hurtig@kau.se> (raw)
In-Reply-To: <cover.1449478261.git.per.hurtig@kau.se>
This is a request for comments.
RTO and TLP restart is a modification to the restart process of the RTO and
TLP timers in TCP. Currently, both timers are restarted with its
corresponding timeout value when an acknowledgment (ACK) for correctly
received data is received. In many situations, resetting the timers on
incoming ACKs will add an implicit offset of at least RTT seconds to the
loss recovery process.
The goal of the modified restart is to provide quicker loss recovery for
segments lost in the end of a burst/connection, where the limited feedback
from a receiver inhibits the use of fast/early retransmit. To accomplish
this the algorithm adjusts the RTO and PTO (TLP's timer) values on each
rearm of the timers to allow them to expire after exactly RTO and PTO ms,
respectively.
The restart behavior is controlled by the new tcp_timer_restart sysctl.
tcp_timer_restart==0; disables RTOR and TLPR.
==1; enables RTOR.
==2; enables TLPR.
==3; enables both RTOR and TLPR. [DEFAULT]
The new restart behavior has been approved by the IETF for publication as
an experimental RFC (for the RTO part of the mechanism) [1], and
experiments have been conducted to show both the benefit of this strategy
(in terms of reduced loss-recovery delays) and the limited negative impact
(in terms of spurious retransmissions) [2]. More information regarding the
mechanism can be found at [3].
Basic functionality tests, using packetdrill, are available at:
https://github.com/perhurt/packetdrill/tree/master/gtests/net/packetdrill/tests/linux/timer_restart
[1] https://datatracker.ietf.org/doc/draft-ietf-tcpm-rtorestart/
[2] http://www.sigcomm.org/sites/default/files/ccr/papers/2015/January/0000000-0000000.pdf
[3] http://riteproject.eu/resources/rto-restart/
Per Hurtig (2):
tcp: RTO Restart (RTOR)
tcp: TLP restart (TLPR)
Documentation/networking/ip-sysctl.txt | 12 ++++++++++++
include/net/tcp.h | 8 +++++++-
net/ipv4/sysctl_net_ipv4.c | 10 ++++++++++
net/ipv4/tcp_input.c | 31 ++++++++++++++++++++++++++++++-
net/ipv4/tcp_output.c | 12 ++++++++++--
5 files changed, 69 insertions(+), 4 deletions(-)
--
1.9.1
next prev parent reply other threads:[~2015-12-08 9:26 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-12-07 9:00 [RFC PATCH net-next 0/2] tcp: timer restart for tail loss Per Hurtig
2015-12-07 9:00 ` [RFC PATCH net-next 1/2] tcp: RTO Restart (RTOR) Per Hurtig
2015-12-07 10:22 ` Ilpo Järvinen
2015-12-07 16:46 ` Marcelo Ricardo Leitner
2015-12-07 17:03 ` Eric Dumazet
2015-12-08 2:05 ` Yuchung Cheng
2015-12-08 9:25 ` Per Hurtig
2015-12-07 9:00 ` [RFC PATCH net-next 2/2] tcp: TLP restart (TLPR) Per Hurtig
2015-12-08 9:19 ` Per Hurtig [this message]
2015-12-08 9:19 ` [RFC PATCHv2 net-next 1/2] tcp: RTO Restart (RTOR) Per Hurtig
2015-12-08 10:50 ` Ilpo Järvinen
2015-12-08 11:03 ` Per Hurtig
2015-12-08 13:47 ` Eric Dumazet
2015-12-10 6:51 ` Per Hurtig
2015-12-10 15:37 ` Neal Cardwell
2015-12-10 21:11 ` Per Hurtig
2015-12-08 9:19 ` [RFC PATCHv2 net-next 2/2] tcp: TLP restart (TLPR) Per Hurtig
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=cover.1449561786.git.per.hurtig@kau.se \
--to=per.hurtig@kau.se \
--cc=anna.brunstrom@kau.se \
--cc=apetlund@simula.no \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=fw@strlen.de \
--cc=ilpo.jarvinen@helsinki.fi \
--cc=michawe@ifi.uio.no \
--cc=mleitner@redhat.com \
--cc=mohammad.rajiullah@kau.se \
--cc=nanditad@google.com \
--cc=ncardwell@google.com \
--cc=netdev@vger.kernel.org \
--cc=pasi.sarolahti@iki.fi \
--cc=stephen@networkplumber.org \
--cc=tom@herbertland.com \
--cc=viro@zeniv.linux.org.uk \
--cc=willemb@google.com \
--cc=ycheng@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).