From: Eric Dumazet <eric.dumazet@gmail.com>
To: "Steinar H. Gunderson" <sgunderson@bigfoot.com>
Cc: Jonathan Morton <chromatix99@gmail.com>,
Neal Cardwell <ncardwell@google.com>,
"aqm@ietf.org" <aqm@ietf.org>,
bloat <bloat@lists.bufferbloat.net>
Subject: Re: [Bloat] TCP BBR paper is now generally available
Date: Sat, 03 Dec 2016 15:09:21 -0800 [thread overview]
Message-ID: <1480806561.18162.432.camel@edumazet-glaptop3.roam.corp.google.com> (raw)
In-Reply-To: <1480806161.18162.429.camel@edumazet-glaptop3.roam.corp.google.com>
On Sat, 2016-12-03 at 15:02 -0800, Eric Dumazet wrote:
> On Sat, 2016-12-03 at 14:55 -0800, Eric Dumazet wrote:
>
> > Perfect.
> >
> > Note that starting from linux-4.4, e1000e gets gro_flush_timeout that
> > would help this precise workload
>
> Also it appears the sender uses a lot of relatively small segments (8220
> bytes at a time), with PSH, so GRO wont be able to help.
>
> I wonder how these PSH are forced.
One possibility would be that the sender is not using fq/pacing,
or some driver is using skb_orphan(), killing TCP Small queue.
-> No pressure on qdisc, auto corking does not trigger,
and application does small writes.
next prev parent reply other threads:[~2016-12-03 23:09 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-12-02 15:52 Dave Taht
2016-12-02 19:15 ` Aaron Wood
2016-12-02 20:32 ` Jonathan Morton
2016-12-02 22:22 ` Neal Cardwell
2016-12-02 22:40 ` Steinar H. Gunderson
2016-12-02 23:31 ` Eric Dumazet
2016-12-03 13:03 ` Neal Cardwell
2016-12-03 19:13 ` Steinar H. Gunderson
2016-12-03 20:20 ` Eric Dumazet
2016-12-03 20:26 ` Jonathan Morton
2016-12-03 21:07 ` Eric Dumazet
2016-12-03 21:34 ` Steinar H. Gunderson
2016-12-03 21:50 ` Eric Dumazet
2016-12-03 22:13 ` Steinar H. Gunderson
2016-12-03 22:55 ` Eric Dumazet
2016-12-03 23:02 ` Eric Dumazet
2016-12-03 23:09 ` Eric Dumazet [this message]
2016-12-03 23:03 ` Steinar H. Gunderson
2016-12-03 23:15 ` Eric Dumazet
2016-12-03 23:24 ` Eric Dumazet
2016-12-04 3:18 ` Neal Cardwell
2016-12-04 8:44 ` Steinar H. Gunderson
2016-12-04 17:13 ` Eric Dumazet
2016-12-04 17:38 ` Steinar H. Gunderson
2016-12-06 17:20 ` Steinar H. Gunderson
2016-12-06 21:31 ` Neal Cardwell
2016-12-03 21:38 ` Jonathan Morton
2016-12-03 21:33 ` Steinar H. Gunderson
2016-12-07 16:28 ` Alan Jenkins
2016-12-07 16:47 ` Steinar H. Gunderson
2016-12-07 17:03 ` Alan Jenkins
2016-12-08 8:24 ` Mikael Abrahamsson
2016-12-08 13:22 ` Dave Täht
2016-12-08 14:01 ` Mikael Abrahamsson
2016-12-08 21:29 ` Neal Cardwell
2016-12-08 22:31 ` Yuchung Cheng
2016-12-09 14:52 ` Klatsky, Carl
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
List information: https://lists.bufferbloat.net/postorius/lists/bloat.lists.bufferbloat.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1480806561.18162.432.camel@edumazet-glaptop3.roam.corp.google.com \
--to=eric.dumazet@gmail.com \
--cc=aqm@ietf.org \
--cc=bloat@lists.bufferbloat.net \
--cc=chromatix99@gmail.com \
--cc=ncardwell@google.com \
--cc=sgunderson@bigfoot.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