CoDel AQM discussions
 help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: dave taht <dave.taht@gmail.com>
Cc: codel@lists.bufferbloat.net, "Dave Täht" <dave.taht@bufferbloat.net>
Subject: Re: [Codel] [PATCH v5] pkt_sched: codel: Controlled Delay AQM
Date: Sun, 06 May 2012 07:18:01 +0200	[thread overview]
Message-ID: <1336281481.3752.994.camel@edumazet-glaptop> (raw)
In-Reply-To: <4FA5B584.2050400@gmail.com>

On Sat, 2012-05-05 at 16:19 -0700, dave taht wrote:

> I don't buy it. See previous mail.
> 
> count - some_x sure.

It depends if some_x is a constant or not.

TCP cwnd is divided by two after a drop.

cwnd = cwnd >> 1;

If we did cwnd = cwnd - some_x; It would no work very well.


I am now experimenting :

q->count = max(1U, q->count - (q->count >> 2));

(count = 75% of count)
 


  reply	other threads:[~2012-05-06  5:18 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-05-05 11:34 [Codel] [PATCH 2/2] Clamp interval to 32 bits Dave Täht
2012-05-05 11:40 ` Dave Taht
2012-05-05 11:53   ` Eric Dumazet
2012-05-05 14:49     ` [Codel] [PATCH v5] pkt_sched: codel: Controlled Delay AQM Eric Dumazet
2012-05-05 16:11       ` Dave Taht
2012-05-05 17:07         ` Eric Dumazet
2012-05-05 17:22           ` Dave Taht
2012-05-05 18:54             ` [Codel] [PATCH iproute2] " Eric Dumazet
2012-05-05 19:08               ` Eric Dumazet
2012-05-05 21:30               ` Eric Dumazet
2012-05-06 18:56                 ` [Codel] [PATCH v8 " Eric Dumazet
2012-05-05 20:20       ` [Codel] [PATCH v5] pkt_sched: " Eric Dumazet
2012-05-05 20:36         ` Eric Dumazet
2012-05-05 21:11           ` Eric Dumazet
2012-05-05 21:12             ` dave taht
2012-05-05 21:20               ` Eric Dumazet
2012-05-05 21:28                 ` [Codel] [PATCH v6] " Eric Dumazet
2012-05-05 21:40                   ` Eric Dumazet
2012-05-05 21:58                   ` Eric Dumazet
2012-05-06 18:52                   ` [Codel] [PATCH v8] " Eric Dumazet
2012-05-06 19:51                     ` Eric Dumazet
2012-05-05 22:03                 ` [Codel] [PATCH v5] " dave taht
2012-05-05 22:09                   ` Eric Dumazet
2012-05-05 22:12                     ` Eric Dumazet
2012-05-05 22:16                       ` dave taht
2012-05-05 22:15                     ` dave taht
2012-05-05 22:34                     ` dave taht
2012-05-05 22:39                       ` Eric Dumazet
2012-05-05 22:48                         ` dave taht
2012-05-05 23:07                           ` Eric Dumazet
2012-05-05 23:19                             ` dave taht
2012-05-06  5:18                               ` Eric Dumazet [this message]
2012-05-05 23:09                           ` dave taht
2012-05-05 23:15                             ` dave taht

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/codel.lists.bufferbloat.net/

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

  git send-email \
    --in-reply-to=1336281481.3752.994.camel@edumazet-glaptop \
    --to=eric.dumazet@gmail.com \
    --cc=codel@lists.bufferbloat.net \
    --cc=dave.taht@bufferbloat.net \
    --cc=dave.taht@gmail.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