From: Dave Taht <dave.taht@gmail.com>
To: Eric Dumazet <eric.dumazet@gmail.com>
Cc: codel@lists.bufferbloat.net, "Dave Täht" <dave.taht@bufferbloat.net>
Subject: Re: [Codel] [PATCH v9] codel: Controlled Delay AQM
Date: Sun, 6 May 2012 22:52:18 -0700 [thread overview]
Message-ID: <CAA93jw5xxX53KgCrcyDDH7ev+_4G2aZr1++s6kGMwV=ZGxkB0Q@mail.gmail.com> (raw)
In-Reply-To: <1336369834.3752.2234.camel@edumazet-glaptop>
On Sun, May 6, 2012 at 10:50 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> On Sun, 2012-05-06 at 22:35 -0700, Dave Täht wrote:
>> This version (9) adds support for various forms of decrease in s3,
>> in the form of the module parameters gentle and decrease_method.
>>
>> It defaults to the algorithm as described in the original presentation.
>>
>> v1: Original implementation - Dave Taht
>> v2: Working code - Corrections for ktime - Dave Taht
>> v3: 32 bit support and port to net-next - Eric Dumazet
>> v4: 16 bit precision for inv sqrt and cache - Dave Taht
>> v5: Kernel cleanup and full precision - Eric Dumazet
>> v6: Dump Stats support added - Eric Dumazet
>> v7: Complete rewrite for u32 values - Eric Dumazet
>> v8: Stats and timing added, 64 bit prescale improved - Eric Dumazet
>> v9: debated functionality moved to isolated routine - Dave Taht
>> ---
>
>> +static u32 gentle = 0;
>> +static u32 decrease_method = 0;
>> +module_param(gentle, uint, 0644);
>> +module_param(decrease_method, uint, 0644);
>> +MODULE_PARM_DESC(gentle,"Gently increment count in massive drop state");
>> +MODULE_PARM_DESC(decrease_method,"Various means of decreasing count");
>
> Hey, thats absolutely forbidden.
>
> Just add new TCA_CODEL_xxx knobs to control things with tc, for each
> qdisc, and not globally on the machine.
>
I regard this addition as a debugging tool, not api functionality, at least
at present...
>
>
> _______________________________________________
> Codel mailing list
> Codel@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/codel
--
Dave Täht
SKYPE: davetaht
US Tel: 1-239-829-5608
http://www.bufferbloat.net
next prev parent reply other threads:[~2012-05-07 5:52 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-05-07 5:35 Dave Täht
2012-05-07 5:50 ` Eric Dumazet
2012-05-07 5:52 ` Dave Taht [this message]
2012-05-07 5:51 ` Dave Taht
2012-05-07 13:57 ` [Codel] [PATCH v10] " Eric Dumazet
2012-05-07 16:07 ` [Codel] [PATCH v1 ] sfq: add a Controlled Delay option Eric Dumazet
2012-05-09 13:50 ` [Codel] [PATCH v12] codel: Controlled Delay AQM Eric Dumazet
2012-05-09 13:54 ` [Codel] [PATCH v12 iproute2] " Eric Dumazet
2012-05-09 15:47 ` [Codel] [PATCH v12] " Dave Taht
2012-05-09 15:54 ` Eric Dumazet
2012-05-09 16:08 ` Dave Taht
2012-05-09 16:14 ` Eric Dumazet
2012-05-09 16:32 ` [Codel] [Bloat] " Josh Hunt
2012-05-09 16:37 ` Eric Dumazet
2012-05-10 17:51 ` [Codel] [PATCH v13 net-next] " Eric Dumazet
2012-05-11 3:36 ` David Miller
2012-05-11 6:01 ` Eric Dumazet
2012-05-14 17:35 ` Simon Barber
2012-05-14 20:08 ` [Codel] [Bloat] " Dave Hart
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='CAA93jw5xxX53KgCrcyDDH7ev+_4G2aZr1++s6kGMwV=ZGxkB0Q@mail.gmail.com' \
--to=dave.taht@gmail.com \
--cc=codel@lists.bufferbloat.net \
--cc=dave.taht@bufferbloat.net \
--cc=eric.dumazet@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