General list for discussing Bufferbloat
 help / color / mirror / Atom feed
From: "Steinar H. Gunderson" <sgunderson@bigfoot.com>
To: Neil Davies <neil.davies@pnsol.com>
Cc: bloat@lists.bufferbloat.net
Subject: Re: [Bloat] Best practices for paced TCP on Linux?
Date: Sat, 7 Apr 2012 17:16:00 +0200	[thread overview]
Message-ID: <20120407151600.GA21452@uio.no> (raw)
In-Reply-To: <8C78AC1F-7305-4623-ADE6-1535CAA1FCBF@pnsol.com>

On Sat, Apr 07, 2012 at 04:08:20PM +0100, Neil Davies wrote:
> That is the general idea - the issue is that the dynamic arrival rate as
> "round trip window size" double just dramatically exceeds the available
> buffering at some intermediate point  - it is self inflicted (intra stream)
> congestion with the effect of dramatically increasing the quality
> attenuation (delay and loss) for streams flowing through that point.

We've been tuning our stream to have more consistent frame sizes (adjusting
the VBV settings); that seems to have alleviated the problems somewhat.

> The packet train may also be an issue, especially if there is h/w assist
> for TCP (which might well be the case here, as the interface was  a 10G
> one, comments Steinar?) - we have observed an interesting phenomena in
> access networks where packet trains arrive (8+ packets back to pack at 10G)
> for service down a low speed (2M) link - this leads to the effective
> transport delay being highly non-stationary - with all that implies for the
> other flows on that link.

The card is a standard Intel 10GigE card, and we've turned off segmentation
offload to avoid this precise issue.

I've also tried hacking VLC to pace out the packets a bit more, but it didn't
really seem to give the effect I had hoped, especially as things sometimes
would glitch even without any packets actually being lost (which would
contradict my “10GigE is too bursty” guess). The VBV tuning was a lot more
efficient.

/* Steinar */
-- 
Homepage: http://www.sesse.net/

  reply	other threads:[~2012-04-07 15:16 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-04-06 21:37 Steinar H. Gunderson
2012-04-06 21:49 ` Dave Taht
2012-04-06 22:21   ` Steinar H. Gunderson
2012-04-07 15:08     ` Eric Dumazet
2012-04-07 15:25       ` Dave Taht
2012-04-07 15:35         ` Steinar H. Gunderson
2012-04-07 15:48           ` Dave Taht
2012-04-07 15:52           ` Dave Taht
2012-04-07 17:10           ` Jonathan Morton
2012-04-07 17:18             ` Dave Taht
2012-04-07 17:44               ` Jonathan Morton
2012-04-07 18:10             ` Steinar H. Gunderson
2012-04-07 18:27               ` Jonathan Morton
2012-04-07 18:56                 ` Dave Taht
2012-04-07 18:50               ` Dave Taht
2012-04-07 18:54                 ` Steinar H. Gunderson
2012-04-07 19:01                   ` Steinar H. Gunderson
2012-04-07 19:08                     ` Jonathan Morton
2012-04-07 19:38                     ` Dave Taht
2012-04-07 20:16                       ` Steinar H. Gunderson
2012-04-14  0:37                       ` Rick Jones
2012-04-07 21:13                     ` Jesper Dangaard Brouer
2012-04-07 21:31                       ` Steinar H. Gunderson
2012-04-07 19:02                   ` Dave Taht
2012-04-07 21:49                 ` Fred Baker
2012-04-07 22:36                   ` Dave Taht
2012-04-07 23:59                     ` Fred Baker
2012-04-07 20:27         ` Neil Davies
2012-04-14  0:35     ` Rick Jones
2012-04-14 21:06       ` Roger Jørgensen
2012-04-16 17:05         ` Rick Jones
2012-04-07 11:54 ` Neil Davies
2012-04-07 14:17   ` Fred Baker
2012-04-07 15:08     ` Neil Davies
2012-04-07 15:16       ` Steinar H. Gunderson [this message]
2012-04-14  0:44     ` Rick Jones
2012-04-07 14:48   ` Dave Taht
2012-05-12 20:08 ` Steinar H. Gunderson

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=20120407151600.GA21452@uio.no \
    --to=sgunderson@bigfoot.com \
    --cc=bloat@lists.bufferbloat.net \
    --cc=neil.davies@pnsol.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